Search Results for author:
Found 194 papers, 54 papers with code
Controlled Text Generation Using Dictionary Prior in Variational Autoencoders
While variational autoencoders (VAEs) have been widely applied in text generation tasks, they are troubled by two challenges: insufficient representation capacity and poor controllability.
MINER: Multi-Interest Matching Network for News Recommendation
Accurately matching user’s interests and candidate news is the key to news recommendation.
Natural Language Processing Meets Quantum Physics: A Survey and Categorization
Recent research has investigated quantum NLP, designing algorithms that process natural language in quantum computers, and also quantum-inspired algorithms that improve NLP performance on classical computers.
MTRec: Multi-Task Learning over BERT for News Recommendation
With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding.
SceneTracker: Long-term Scene Flow Estimation Network
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE).
Reasoning-Enhanced Object-Centric Learning for Videos
Object-centric learning aims to break down complex visual scenes into more manageable object representations, enhancing the understanding and reasoning abilities of machine learning systems toward the physical world.
Bilateral Propagation Network for Depth Completion
Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image.
Rethinking The Uniformity Metric in Self-Supervised Learning
Uniformity plays a crucial role in the assessment of learned representations, contributing to a deeper comprehension of self-supervised learning.
SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model
To alleviate artifacts and improve quality of synthetic images, we fine-tune Vision-Language Model (VLM) as artifact classifier to automatically identify and classify a wide range of artifacts and provide supervision for further optimizing generative models.
Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
Meanwhile, we propose a novel tool sampling strategy to enhance the generalizability of LLMs over unseen tools.
Are Large Language Models Good Prompt Optimizers?
Despite the success, the underlying mechanism of this approach remains unexplored, and the true effectiveness of LLMs as Prompt Optimizers requires further validation.
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition
To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton based action recognition is first investigated.
Distilling Mathematical Reasoning Capabilities into Small Language Models
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
Evaluating and Enhancing Large Language Models Performance in Domain-specific Medicine: Osteoarthritis Management with DocOA
This study focused on evaluating and enhancing the clinical capabilities of LLMs in specific domains, using osteoarthritis (OA) management as a case study.
FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning
This work is pioneering in the execution of instruction fine-tuning on a sparse expert-mixed model, marking a significant breakthrough in enhancing the capabilities of this model architecture.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations
Decentralized learning has emerged as an alternative method to the popular parameter-server framework which suffers from high communication burden, single-point failure and scalability issues due to the need of a central server.
Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints
Restless multi-armed bandits (RMAB) have been widely used to model sequential decision making problems with constraints.
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
We conducted extensive experiments with a 2-billion parameter USM on a large-scale voice search dataset to evaluate our proposed method.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion
Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion.
GLIME: General, Stable and Local LIME Explanation
Additionally, LIME's sampling neighborhood is non-local and biased towards the reference, resulting in poor local fidelity and sensitivity to reference choice.
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV).
Ranked #1 on
Semantic Segmentation
on LaRS
Trustworthy AI: Deciding What to Decide
We aim to use this framework to conduct the TAI experiments by quantitive and qualitative research methods to satisfy TAI properties for the decision-making context.
Adversarial Preference Optimization
Human preference alignment is essential to improve the interaction quality of large language models (LLMs).
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps.
JOSA: Joint surface-based registration and atlas construction of brain geometry and function
By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of the brain structure and function.
Efficient online cross-covariance monitoring with incremental SVD: An approach for the detection of emerging dependency patterns in IoT systems
The development of the manufacturing systems has made it increasingly necessary to monitor the data generated by multiple interconnected subsystems with rapid incoming of samples.
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al).
Interpretable AI-Driven Discovery of Terrain-Precipitation Relationships for Enhanced Climate Insights
Through this AI-driven knowledge discovery, we uncover previously undisclosed explicit equations that shed light on the connection between terrain features and precipitation patterns.
A Real-time Faint Space Debris Detector With Learning-based LCM
In conclusion, the algorithm in this paper is of high speed and precision, which guarantees its promising applications in the extraction of high dynamic targets.
Interpretable and Efficient Beamforming-Based Deep Learning for Single Snapshot DOA Estimation
We introduce an interpretable deep learning approach for direction of arrival (DOA) estimation with a single snapshot.
IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making
Market making (MM) has attracted significant attention in financial trading owing to its essential function in ensuring market liquidity.
A Survey on Model Compression for Large Language Models
As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations.
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices.
ReIDTrack: Multi-Object Track and Segmentation Without Motion
Association techniques mainly depend on the combination of motion and appearance information.
PVG: Progressive Vision Graph for Vision Recognition
Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects.
Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
To increase the adaptability of ACCID, we propose a splicing-based synthetic character algorithm to augment the training samples and apply an image denoising method to improve the image quality.
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE).
Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates
With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular parameter server framework.
Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization
To address this challenge, we propose a mixed-precision post training quantization (PTQ) approach that assigns different numerical precisions to tensors in a network based on their specific needs, for a reduced memory footprint and improved latency while preserving model accuracy.
Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.
2-bit Conformer quantization for automatic speech recognition
With the large-scale training data, we obtain a 2-bit Conformer model with over 40% model size reduction against the 4-bit version at the cost of 17% relative word error rate degradation
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance
To this end, we provide a fine-grained analysis of bias in GBDT and demonstrate that the bias originates from 1) the systematic bias in the gain estimation of each split and 2) the bias in the split finding algorithm resulting from the use of the same data to evaluate the split improvement and determine the best split.
PaLM 2 Technical Report
Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.
Ranked #1 on
Question Answering
on StrategyQA
Generative Table Pre-training Empowers Models for Tabular Prediction
Recently, the topic of table pre-training has attracted considerable research interest.
Towards Generalizable Reinforcement Learning for Trade Execution
To evaluate our algorithms, we also implement a carefully designed simulator based on historical limit order book (LOB) data to provide a high-fidelity benchmark for different algorithms.
MolKD: Distilling Cross-Modal Knowledge in Chemical Reactions for Molecular Property Prediction
This paper studies this problem and proposes to incorporate chemical domain knowledge, specifically related to chemical reactions, for learning effective molecular representations.
Robust Neural Architecture Search
Neural Architectures Search (NAS) becomes more and more popular over these years.
Joint cortical registration of geometry and function using semi-supervised learning
Brain surface-based image registration, an important component of brain image analysis, establishes spatial correspondence between cortical surfaces.
Information extraction and artwork pricing
Traditional art pricing models often lack fine measurements of painting content.
Learning from Noisy Labels with Decoupled Meta Label Purifier
Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability.
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms.
Ranked #2 on
Image Classification
on Clothing1M
(using extra training data)
Improving Differentiable Architecture Search via Self-Distillation
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.
Operation-level Progressive Differentiable Architecture Search
It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.
Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search
In this paper, we propose a method to efficiently determine quantization configurations of different tensors in ML models using post-training mixed precision quantization.
Rethinking Mobile Block for Efficient Attention-based Models
This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance.
FCC: Feature Clusters Compression for Long-Tailed Visual Recognition
Through representation learning, DNNs can map BFs into dense clusters in feature space, while the features of minority classes often show sparse clusters.
Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits
Most research for this problem focuses exclusively on the settings that players have \textit{full access} to all arms and receive no reward when pulling the same arm.
Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models
This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network.
OpenFE: Automated Feature Generation with Expert-level Performance
In the two competitions, features generated by OpenFE with a simple baseline model can beat 99. 3% and 99. 6% data science teams respectively.
Knowledge-Guided Exploration in Deep Reinforcement Learning
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP).
Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning
In this paper, we formulate the APP-installation user embedding learning into a bipartite graph embedding problem.
DIGAT: Modeling News Recommendation with Dual-Graph Interaction
Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.
MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization
We evaluate the proposed approach on three real-world index datasets and compare it to state-of-the-art baselines.
Large-step neural network for learning the symplectic evolution from partitioned data
Based on Chen & Tao (2021), the symplectic mapping is represented by a generating function.
Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization
We provide a clean and tight analysis of ProxSVRG+, which shows that it outperforms the deterministic proximal gradient descent (ProxGD) for a wide range of minibatch sizes, hence solves an open problem proposed in Reddi et al. (2016b).
Waveform Design for Mutual Interference Mitigation in Automotive Radar
The mutual interference between similar radar systems can result in reduced radar sensitivity and increased false alarm rates.
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
Based on this empirical observation, we attempt to theoretically and empirically explain the dynamics of various key quantities that lead to the change of sharpness in each phase of EOS.
Efficient Algorithms for Sparse Moment Problems without Separation
Our algorithm for the one-dimensional problem (also called the sparse Hausdorff moment problem) is a robust version of the classic Prony's method, and our contribution mainly lies in the analysis.
Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning
Moreover, to improve data efficiency and provide better generalization performance, we train the policy model with augmented data (e. g., noisy BSM and noisy surveillance images).
Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures
It uses less than 5% FLOPS compared with previous SOTA methods on the largest benchmark dataset.
FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns
As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment.
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e. g.}, greedy search).
Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model
In this work, a novel coupled theory-guided neural network (TgNN) based surrogate model is built to facilitate computation efficiency under the premise of satisfactory accuracy.
Generalization Bounds for Gradient Methods via Discrete and Continuous Prior
In this paper, we introduce a new discrete data-dependent prior to the PAC-Bayesian framework, and prove a high probability generalization bound of order $O(\frac{1}{n}\cdot \sum_{t=1}^T(\gamma_t/\varepsilon_t)^2\left\|{\mathbf{g}_t}\right\|^2)$ for Floored GD (i. e. a version of gradient descent with precision level $\varepsilon_t$), where $n$ is the number of training samples, $\gamma_t$ is the learning rate at step $t$, $\mathbf{g}_t$ is roughly the difference of the gradient computed using all samples and that using only prior samples.
ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification
Motivated by this observation, we propose a principled GCL framework on Imbalanced node classification (ImGCL), which automatically and adaptively balances the representations learned from GCL without labels.
Ridgeless Regression with Random Features
Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.
Sharper Utility Bounds for Differentially Private Models
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
Stability and Generalization of Differentially Private Minimax Problems
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation
Using this structural result, we establish the indexability of our problem, and employ the Whittle index policy to minimize average latency.
ASFD: Automatic and Scalable Face Detector
Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection.
Ranked #1 on
Face Detection
on WIDER Face (Medium)
Machine learning prediction for mean motion resonance behaviour -- The planar case
Most recently, machine learning has been used to study the dynamics of integrable Hamiltonian systems and the chaotic 3-body problem.
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.
Convolution of Convolution: Let Kernels Spatially Collaborate
In the biological visual pathway, especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly.
DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities
Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading.
AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020
Graph Neural Networks (GNNs) have become increasingly popular and achieved impressive results in many graph-based applications.
ML-EXray: Visibility into ML Deployment on the Edge
The key challenge is that there is not much visibility into ML inference execution on edge devices, and very little awareness of potential issues during the edge deployment process.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
We demonstrate that both temporal grains are beneficial to atomic action recognition.
FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding
The few-shot natural language understanding (NLU) task has attracted much recent attention.
Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits
We call it the R(MA)^2B-UCB algorithm.
Critical Learning Periods in Federated Learning
In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i. e., FL exhibits critical learning periods, in which small gradient errors can have irrecoverable impact on the final test accuracy.
Unsupervised Open-Domain Question Answering
Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner.
Machine Reading Comprehension
Open-Domain Question Answering
Analyzing and Mitigating Interference in Neural Architecture Search
In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe: 1) the interference on a shared operator between two child models is positively correlated with the number of different operators; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar.
Accelerating Serverless Computing by Harvesting Idle Resources
Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions.
FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning
Most previous methods for text data augmentation are limited to simple tasks and weak baselines.
Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling
In a set of experiments on three real-world financial markets: stocks, cryptocurrencies, and ETFs, LARA significantly outperforms several machine learning based methods on the Qlib quantitative investment platform.
Discrete Auto-regressive Variational Attention Models for Text Modeling
We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse.
Simple Combinatorial Algorithms for Combinatorial Bandits: Corruptions and Approximations
Our algorithm achieves an (approximation) regret bound of $\tilde{O}\left(d\sqrt{KT}\right)$.
AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange
In this paper, we propose to substitute these redundant channels with other informative channels to achieve this goal.
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.
NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search
The technical challenge of NAS-BERT is that training a big supernet on the pre-training task is extremely costly.
Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.
Weighted SPICE Algorithms for Range-Doppler Imaging Using One-Bit Automotive Radar
The recently proposed hyperparameter-free (and hence user friendly) weighted SPICE algorithms, including SPICE, LIKES, SLIM and IAA, achieve excellent parameter estimation performance for data sampled with high precision.
Sinusoidal Parameter Estimation from Signed Measurements via Majorization-Minimization Based RELAX
In a previous paper, a relaxation-based algorithm, referred to as 1bRELAX, has been proposed to iteratively maximize the likelihood function.
Joint RFI Mitigation and Radar Echo Recovery for One-Bit UWB Radar
Radio frequency interference (RFI) mitigation and radar echo recovery are critically important for the proper functioning of ultra-wideband (UWB) radar systems using one-bit sampling techniques.
Both qubits of the singlet state can be steered simultaneously by multiple independent observers via sequential measurement
Quantum correlation is a fundamental property which distinguishes quantum systems from classical ones, and it is also a fragile resource under projective measurement.
Quantum Physics
Return-Based Contrastive Representation Learning for Reinforcement Learning
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL).
RFI Mitigation for One-bit UWB Radar Systems
A one-bit UWB system obtains its signed measurements via a low-cost and high rate sampling scheme, referred to as the Continuous Time Binary Value (CTBV) technology.
Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers
In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset.
Investigating the nature of MGRO J1908+06 with multiwavelength observations
The unidentified TeV source MGRO J1908+06, with emission extending from hundreds of GeV to beyond 100TeV, is one of the most intriguing sources in the Galactic plane.
High Energy Astrophysical Phenomena
Observation of ultra-slow shock waves in a tunable magnetic lattice
The combination of fast propagation speeds and highly localized nature has hindered the direct observation of the evolution of shock waves at the molecular scale.
Soft Condensed Matter
On the quantization of recurrent neural networks
Integer quantization of neural networks can be defined as the approximation of the high precision computation of the canonical neural network formulation, using reduced integer precision.
Learning Augmented Index Policy for Optimal Service Placement at the Network Edge
We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service.
Theory of polymer diffusion in polymer-nanoparticle mixtures: effect of nanoparticle concentration and polymer length
The dynamics of polymer-nanoparticle (NP) mixtures, which involves multiple scales and system-specific variables, has posed a long-standing challenge on its theoretical description.
Soft Condensed Matter
Distributed Stochastic Consensus Optimization with Momentum for Nonconvex Nonsmooth Problems
While many distributed optimization algorithms have been proposed for solving smooth or convex problems over the networks, few of them can handle non-convex and non-smooth problems.
TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems
We introduce TensorFlow Lite Micro (TF Micro), an open-source ML inference framework for running deep-learning models on embedded systems.
DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis
Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns.
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors.
Loosely Coupled Federated Learning Over Generative Models
This paper proposes Loosely Coupled Federated Learning (LC-FL), a framework using generative models as transmission media to achieve low communication cost and heterogeneous federated learning.
Secure Transmission by Leveraging Multiple Intelligent Reflecting Surfaces in MISO Systems
Specifically, to guarantee the worst-case achievable secrecy rate among multiple legitimate users, we formulate a max-min problem that can be solved by an alternative optimization method to decouple it into multiple sub-problems.
LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition
However, there are more than 6, 000 languages in the world and most languages are lack of speech training data, which poses significant challenges when building TTS and ASR systems for extremely low-resource languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
ACFD: Asymmetric Cartoon Face Detector
Cartoon face detection is a more challenging task than human face detection due to many difficult scenarios is involved.
Neural Architecture Optimization with Graph VAE
The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.
Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
In the planning phase, the agent computes a good policy for any reward function based on the dataset without further interacting with the environment.
Improved Algorithms for Convex-Concave Minimax Optimization
This paper studies minimax optimization problems $\min_x \max_y f(x, y)$, where $f(x, y)$ is $m_x$-strongly convex with respect to $x$, $m_y$-strongly concave with respect to $y$ and $(L_x, L_{xy}, L_y)$-smooth.
ASFD: Automatic and Scalable Face Detector
In this paper, we propose a novel Automatic and Scalable Face Detector (ASFD), which is based on a combination of neural architecture search techniques as well as a new loss design.
Meta-Embeddings Based On Self-Attention
Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform meta-embeddings have shown to be beneficial.
Convolutional Spectral Kernel Learning
Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.
Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art
Nowadays, devices are equipped with advanced sensors with higher processing/computing capabilities.
Data Heterogeneity Differential Privacy: From Theory to Algorithm
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).
PA-Cache: Evolving Learning-Based Popularity-Aware Content Caching in Edge Networks
Compared to the conventional content delivery networks, caches in edge networks with smaller sizes usually have to accommodate more bursty requests.
Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice
We obtain both deterministic and randomized online algorithms with provably improved performance when either a single or multiple ML predictions are used to make decisions.
AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment
The multi-factor model is a widely used model in quantitative investment.
Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web
The key concept is to cover the space of possible compound queries on the database with a large number of in-domain questions synthesized with the help of a corpus of generic query templates.
Neuron Interaction Based Representation Composition for Neural Machine Translation
Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors.
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.
Ranked #7 on
Temporal Action Localization
on FineAction
Metric Classification Network in Actual Face Recognition Scene
In this paper, we train a validation classifier to normalize the decision threshold, which means that the result can be obtained directly without replacing the threshold.
Optimizing Speech Recognition For The Edge
While most deployed speech recognition systems today still run on servers, we are in the midst of a transition towards deployments on edge devices.
Semi-supervised Vector-valued Learning: Improved Bounds and Algorithms
Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-task learning and transfer learning.
Automated Spectral Kernel Learning
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.
Learning Guided Convolutional Network for Depth Completion
It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion.
NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization
Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.
AddGraph_ Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN
Anomaly detection in dynamic graphs becomes very critical in many different application scenarios, e. g., recommender systems, while it also raises huge challenges due to the high flexible nature of anomaly and lack of sufficient labelled data.
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations.
Towards Sharp Analysis for Distributed Learning with Random Features
In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.
Relation Extraction with Temporal Reasoning Based on Memory Augmented Distant Supervision
This paper formulates the problem of relation extraction with temporal reasoning and proposes a solution to predict whether two given entities participate in a relation at a given time spot.
Policy Search by Target Distribution Learning for Continuous Control
We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process.
Robust Variational Autoencoder
Machine learning methods often need a large amount of labeled training data.
Anti-Confusing: Region-Aware Network for Human Pose Estimation
In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation.
Automatic Target Recognition Using Discrimination Based on Optimal Transport
The use of distances based on optimal transportation has recently shown promise for discrimination of power spectra.
Information Aggregation for Multi-Head Attention with Routing-by-Agreement
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces.
Outcome-Driven Clustering of Acute Coronary Syndrome Patients using Multi-Task Neural Network with Attention
The results demonstrate cluster analysis using outcome-driven multi-task neural network as promising for patient classification and subtyping.
Context-Aware Self-Attention Networks
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies.
Efficient Cross-Validation for Semi-Supervised Learning
In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).
On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning
We develop a new framework, termed Bayes-Stability, for proving algorithm-dependent generalization error bounds.
Max-Diversity Distributed Learning: Theory and Algorithms
We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.
Learning Features of Network Structures Using Graphlets
In this paper, we explore the role of \emph{graphlets} in network classification for both static and temporal networks.
Multi-Class Learning: From Theory to Algorithm
In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.
DSFD: Dual Shot Face Detector
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.
Ranked #1 on
Face Detection
on FDDB
Multi-Head Attention with Disagreement Regularization
Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions.
Guided Exploration in Deep Reinforcement Learning
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of \textit{state-action permissibility} (SAP).
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization
Besides, if the hyperparameters (e. g., the Lipschitz smooth parameter $L$) are not available, we propose a guessing algorithm for guessing them dynamically and also prove a similar convergence rate.
Network Classification in Temporal Networks Using Motifs
Network classification has a variety of applications, such as detecting communities within networks and finding similarities between those representing different aspects of the real world.
BRITS: Bidirectional Recurrent Imputation for Time Series
It is ubiquitous that time series contains many missing values.
General Classification
Multivariate Time Series Forecasting
+5
Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference
In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics.
Gradient Boosting With Piece-Wise Linear Regression Trees
We show that PL Trees can accelerate convergence of GBDT and improve the accuracy.
A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization
In particular, ProxSVRG+ generalizes the best results given by the SCSG algorithm, recently proposed by [Lei et al., 2017] for the smooth nonconvex case.
Code Completion with Neural Attention and Pointer Networks
Intelligent code completion has become an essential research task to accelerate modern software development.
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
This work lays the theoretical foundation for skip-gram based network embedding methods, leading to a better understanding of latent network representation learning.
Generative Adversarial Mapping Networks
They fit generative models by minimizing certain distance measure between the real image distribution and the generated data distribution.
Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
We provide a novel instance-wise lower bound for the sample complexity of the problem, as well as a nontrivial sampling algorithm, matching the lower bound up to a factor of $\ln|\mathcal{F}|$.
SVM via Saddle Point Optimization: New Bounds and Distributed Algorithms
Our algorithms achieve $(1-\epsilon)$-approximations with running time $\tilde{O}(nd+n\sqrt{d / \epsilon})$ for both variants, where $n$ is the number of points and $d$ is the dimensionality.
Practical Algorithms for Best-K Identification in Multi-Armed Bandits
In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions.
Single-Pass PCA of Large High-Dimensional Data
Principal component analysis (PCA) is a fundamental dimension reduction tool in statistics and machine learning.
Learning Gradient Descent: Better Generalization and Longer Horizons
Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters.
Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection
In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution.
Generalized Haar Filter based Deep Networks for Real-Time Object Detection in Traffic Scene
This paper presents a generalized Haar filter based deep network which is suitable for the object detection tasks in traffic scene.
Optimal In-Place Suffix Sorting
The open problem asked to design in-place algorithms in $o(n\log n)$ time and ultimately, in $O(n)$ time for (read-only) integer alphabets with $|\Sigma| \leq n$.
Data Structures and Algorithms
Combinatorial Multi-Armed Bandit with General Reward Functions
Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.
Towards Instance Optimal Bounds for Best Arm Identification
$H(I)=\sum_{i=2}^n\Delta_{[i]}^{-2}$ is the complexity of the instance.
Characterizing Driving Styles with Deep Learning
Characterizing driving styles of human drivers using vehicle sensor data, e. g., GPS, is an interesting research problem and an important real-world requirement from automotive industries.
Store Location Selection via Mining Search Query Logs of Baidu Maps
In this paper, we propose a Demand Distribution Driven Store Placement (D3SP) framework for business store placement by mining search query data from Baidu Maps.
Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture
The best arm identification problem (BEST-1-ARM) is the most basic pure exploration problem in stochastic multi-armed bandits.
Pure Exploration of Multi-armed Bandit Under Matroid Constraints
In a Best-Basis instance, we are given $n$ stochastic arms with unknown reward distributions, as well as a matroid $\mathcal{M}$ over the arms.
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain
First, we consider saliency detection as a frequency domain analysis problem.
Stochastic Online Greedy Learning with Semi-bandit Feedbacks
We further show that the bound is tight in $T$ and other problem instance parameters.
On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs
This paper discusses how to efficiently choose from $n$ unknowndistributions the $k$ ones whose means are the greatest by a certainmetric, up to a small relative error.
On the Optimal Sample Complexity for Best Arm Identification
The $i$th arm has a reward distribution $D_i$ with an unknown mean $\mu_{i}$.
Learning Arbitrary Statistical Mixtures of Discrete Distributions
We study the problem of learning from unlabeled samples very general statistical mixture models on large finite sets.
Matroid and Knapsack Center Problems
We also consider the outlier version of the problem where a given number of vertices can be excluded as the outliers from the solution.
Data Structures and Algorithms Discrete Mathematics
Parallelizing Support Vector Machines on Distributed Computers
Support Vector Machines (SVMs) suffer from a widely recognized scalability problem in both memory use and computational time.
