Search Results for author:
Found 91 papers, 11 papers with code
Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network
Federated learning is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server.
Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit
We study a robust multi-agent multi-armed bandit problem where multiple clients or participants are distributed on a fully decentralized blockchain, with the possibility of some being malicious.
Unsupervised Video Summarization
This paper introduces a new, unsupervised method for automatic video summarization using ideas from generative adversarial networks but eliminating the discriminator, having a simple loss function, and separating training of different parts of the model.
On the Second-Order Convergence of Biased Policy Gradient Algorithms
Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points.
Use of Deep Neural Networks for Uncertain Stress Functions with Extensions to Impact Mechanics
Stress-strain curves, or more generally, stress functions, are an extremely important characterization of a material's mechanical properties.
IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation
Extensive experiments show the effectiveness of group accuracy estimation on model calibration and model selection.
Regret Lower Bounds in Multi-agent Multi-armed Bandit
Multi-armed Bandit motivates methods with provable upper bounds on regret and also the counterpart lower bounds have been extensively studied in this context.
An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Trading
We propose an ensemble method to improve the generalization performance of trading strategies trained by deep reinforcement learning algorithms in a highly stochastic environment of intraday cryptocurrency portfolio trading.
Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints
This paper proposes a novel multi-agent reinforcement learning (MARL) method to learn multiple coordinated agents under directed acyclic graph (DAG) constraints.
S-Omninet: Structured Data Enhanced Universal Multimodal Learning Architecture
In this work, we extend and improve Omninet, an architecture that is capable of handling multiple modalities and tasks at a time, by introducing cross-cache attention, integrating patch embeddings for vision inputs, and supporting structured data.
Early Classifying Multimodal Sequences
Often pieces of information are received sequentially over time.
A Policy for Early Sequence Classification
Sequences are often not received in their entirety at once, but instead, received incrementally over time, element by element.
Multi-Layer Attention-Based Explainability via Transformers for Tabular Data
We propose a graph-oriented attention-based explainability method for tabular data.
Gradient-Boosted Based Structured and Unstructured Learning
Our proposed frameworks allow joint learning on both kinds of data by integrating the paradigms of boosting models and deep neural networks.
Feature Acquisition using Monte Carlo Tree Search
Feature acquisition algorithms address the problem of acquiring informative features while balancing the costs of acquisition to improve the learning performances of ML models.
Pareto Regret Analyses in Multi-objective Multi-armed Bandit
We study Pareto optimality in multi-objective multi-armed bandit by providing a formulation of adversarial multi-objective multi-armed bandit and defining its Pareto regrets that can be applied to both stochastic and adversarial settings.
A Primal-Dual Algorithm for Hybrid Federated Learning
Furthermore, we provide experimental results that demonstrate the performance improvements of the algorithm over a commonly used method in federated learning, FedAvg, and an existing hybrid FL algorithm, HyFEM.
Divergence Results and Convergence of a Variance Reduced Version of ADAM
Under a variance reduction assumption, we show that an ADAM-type algorithm converges, which means that it is the variance of gradients that causes the divergence of original ADAM.
Large-Scale Multi-Document Summarization with Information Extraction and Compression
We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents.
Tricks and Plugins to GBM on Images and Sequences
Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years.
Topic Analysis for Text with Side Data
In the context of text, the neural network provides an overview distribution about side data for the corresponding text, which is the prior distribution in LDA to help perform topic grouping.
Open-Set Recognition of Breast Cancer Treatments
Open-set recognition generalizes a classification task by classifying test samples as one of the known classes from training or "unknown."
Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation
The proposed algorithm directs the parameters of the compressed model toward a flatter solution by exploring the spectral radius of Hessian which results in better generalization on unseen data.
Aggregation Delayed Federated Learning
Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices.
Logit-based Uncertainty Measure in Classification
We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty.
A Probabilistic Approach to Neural Network Pruning
Neural network pruning techniques reduce the number of parameters without compromising predicting ability of a network.
Non-Convex Optimization with Spectral Radius Regularization
We develop a regularization method which finds flat minima during the training of deep neural networks and other machine learning models.
Classification Models for Partially Ordered Sequences
Many models such as Long Short Term Memory (LSTMs), Gated Recurrent Units (GRUs) and transformers have been developed to classify time series data with the assumption that events in a sequence are ordered.
The Impact of the Mini-batch Size on the Dynamics of SGD: Variance and Beyond
We study mini-batch stochastic gradient descent (SGD) dynamics under linear regression and deep linear networks by focusing on the variance of the gradients only given the initial weights and mini-batch size, which is the first study of this nature.
Open Set Domain Adaptation by Extreme Value Theory
In this paper, we tackle the open set domain adaptation problem under the assumption that the source and the target label spaces only partially overlap, and the task becomes when the unknown classes exist, how to detect the target unknown classes and avoid aligning them with the source domain.
Concept Drift and Covariate Shift Detection Ensemble with Lagged Labels
Extensive experiments on structured and unstructured data for different type of data changes establish that our method consistently outperforms the state-of-the-art methods by a large margin.
Inverse Classification with Limited Budget and Maximum Number of Perturbed Samples
In this study, we propose a new framework to solve inverse classification that maximizes the number of perturbed samples subject to a per-feature-budget limits and favorable classification classes of the perturbed samples.
Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms
We propose a new algorithm, namely EXP4. P, by modifying EXP4 and establish its upper bound of regret in both bounded and unbounded sub-Gaussian contextual bandit settings.
Efficient Architecture Search for Continual Learning
To reach these goals, we propose a novel approach named as Continual Learning with Efficient Architecture Search, or CLEAS in short.
Open-Set Recognition with Gaussian Mixture Variational Autoencoders
In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class.
Neural Network Retraining for Model Serving
We address two challenges of life-long retraining: catastrophic forgetting and efficient retraining.
The Impact of the Mini-batch Size on the Variance of Gradients in Stochastic Gradient Descent
The mini-batch stochastic gradient descent (SGD) algorithm is widely used in training machine learning models, in particular deep learning models.
Keyword-based Topic Modeling and Keyword Selection
The challenge is that these need to be specified ahead of knowing the forthcoming documents and the underlying topics.
Listwise Learning to Rank by Exploring Unique Ratings
We encode all of the documents already selected by an RNN model.
Conditional Hierarchical Bayesian Tucker Decomposition for Genetic Data Analysis
We apply these models to examine patients with one of four common types of cancer (breast, lung, prostate, and colorectal) and siblings with and without autism spectrum disorder.
Layer Flexible Adaptive Computation Time for Recurrent Neural Networks
Deep recurrent neural networks perform well on sequence data and are the model of choice.
Mixture-based Multiple Imputation Model for Clinical Data with a Temporal Dimension
The problem of missing values in multivariable time series is a key challenge in many applications such as clinical data mining.
Data Extraction from Charts via Single Deep Neural Network
Automatic data extraction from charts is challenging for two reasons: there exist many relations among objects in a chart, which is not a common consideration in general computer vision problems; and different types of charts may not be processed by the same model.
Dynamic Cell Structure via Recursive-Recurrent Neural Networks
In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps.
Scale Invariant Power Iteration
In this work, we introduce a new class of optimization problems called scale invariant problems and prove that they can be efficiently solved by scale invariant power iteration (SCI-PI) with a generalized convergence guarantee of power iteration.
Convergence Analyses of Online ADAM Algorithm in Convex Setting and Two-Layer ReLU Neural Network
We cover the convex setting showing the regret of the order of the square root of the size of the window in the constant and dynamic learning rate scenarios.
Automatic Ontology Learning from Domain-Specific Short Unstructured Text Data
Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatically learns a domain specific ontology from data.
Autoencoders and Generative Adversarial Networks for Imbalanced Sequence Classification
In addition to the medical device dataset, we also evaluate the GAN-AE performance on two additional datasets and demonstrate the application of GAN-AE to a sequence-to-sequence task where both synthetic sequence inputs and sequence outputs must be generated.
Layer Flexible Adaptive Computational Time
Deep recurrent neural networks perform well on sequence data and are the model of choice.
Unified recurrent network for many feature types
We also include two types of static (whole sequence level) features, one related to time and one not, which are combined with the encoder output.
Combined convolutional and recurrent neural networks for hierarchical classification of images
Deep learning models based on CNNs are predominantly used in image classification tasks.
Unified recurrent neural network for many feature types
We also include two types of static (whole sequence level) features, one related to time and one not, which are combined with the encoder output.
Nested multi-instance classification
We also introduce a method to replace instances that are missing which successfully creates neutral input instances and consistently outperforms standard fill-in methods in real world use cases.
Dynamic Prediction Length for Time Series with Sequence to Sequence Networks
Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length.
Forecasting Crime with Deep Learning
With our best model we are able to predict the correct bin for overall crime count with 75. 6% and 65. 3% accuracy for Chicago and Portland, respectively.
Bayesian active learning for choice models with deep Gaussian processes
In this paper, we propose an active learning algorithm and models which can gradually learn individual's preference through pairwise comparisons.
k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks
In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors model, which generate a sequence of labels, a sequence of out-of-sample feature vectors and a final label for classification, and thus they could also function as oversamplers.
Improved Classification Based on Deep Belief Networks
For better classification generative models are used to initialize the model and model features before training a classifier.
A Stochastic Large-scale Machine Learning Algorithm for Distributed Features and Observations
As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing.
Truth Validation with Evidence
The proposed system provides supporting evidence when the statement is tagged as false.
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
Compared to previous works that decouple agents in the game by assuming optimality in expert strategies, we introduce a new objective function that directly pits experts against Nash Equilibrium strategies, and we design an algorithm to solve for the reward function in the context of inverse reinforcement learning with deep neural networks as model approximations.
Generative Adversarial Nets for Multiple Text Corpora
Generative adversarial nets (GANs) have been successfully applied to the artificial generation of image data.
OSTSC: Over Sampling for Time Series Classification in R
The OSTSC package is a powerful oversampling approach for classifying univariant, but multinomial time series data in R. This article provides a brief overview of the oversampling methodology implemented by the package.
A Simple and Fast Algorithm for L1-norm Kernel PCA
We present an algorithm for L1-norm kernel PCA and provide a convergence analysis for it.
Semantic Document Distance Measures and Unsupervised Document Revision Detection
In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances.
Unsupervised Terminological Ontology Learning based on Hierarchical Topic Modeling
In this paper, we present hierarchical relationbased latent Dirichlet allocation (hrLDA), a data-driven hierarchical topic model for extracting terminological ontologies from a large number of heterogeneous documents.
Online Adaptive Machine Learning Based Algorithm for Implied Volatility Surface Modeling
In this work, we design a machine learning based method, online adaptive primal support vector regression (SVR), to model the implied volatility surface (IVS).
Improving the Expected Improvement Algorithm
To overcome this shortcoming, we introduce a simple modification of the expected improvement algorithm.
Diminishing Batch Normalization
Our proposed DBN algorithm remains the overall structure of the original BN algorithm while introduces a weighted averaging update to some trainable parameters.
Activation Ensembles for Deep Neural Networks
We propose a new methodology of designing activation functions within a neural network at each layer.
An Attention-Based Deep Net for Learning to Rank
In information retrieval, learning to rank constructs a machine-based ranking model which given a query, sorts the search results by their degree of relevance or importance to the query.
Semi-supervised Learning for Discrete Choice Models
Two classic semi-supervised learning algorithms, the expectation maximization algorithm and the cluster-and-label algorithm, have been adapted to our choice modeling problem setting.
Subset Selection for Multiple Linear Regression via Optimization
For high dimensional cases, an iterative heuristic algorithm is proposed based on the mathematical programming models and a core set concept, and a randomized version of the algorithm is derived to guarantee convergence to the global optimum.
Bayesian Network Learning via Topological Order
We propose a mixed integer programming (MIP) model and iterative algorithms based on topological orders to solve optimization problems with acyclic constraints on a directed graph.
Optimization for Large-Scale Machine Learning with Distributed Features and Observations
As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing.
Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories
In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories.
Iteratively Reweighted Least Squares Algorithms for L1-Norm Principal Component Analysis
Principal component analysis (PCA) is often used to reduce the dimension of data by selecting a few orthonormal vectors that explain most of the variance structure of the data.
Regularization for Unsupervised Deep Neural Nets
Unsupervised neural networks, such as restricted Boltzmann machines (RBMs) and deep belief networks (DBNs), are powerful tools for feature selection and pattern recognition tasks.
Rapid Prediction of Player Retention in Free-to-Play Mobile Games
Predicting and improving player retention is crucial to the success of mobile Free-to-Play games.
An Aggregate and Iterative Disaggregate Algorithm with Proven Optimality in Machine Learning
We propose a clustering-based iterative algorithm to solve certain optimization problems in machine learning, where we start the algorithm by aggregating the original data, solving the problem on aggregated data, and then in subsequent steps gradually disaggregate the aggregated data.
Algorithms for Generalized Cluster-wise Linear Regression
We examine the performance of our algorithms on a stock keeping unit (SKU) clustering problem employed in forecasting halo and cannibalization effects in promotions using real-world retail data from a large supermarket chain.
A Semi-supervised learning approach to enhance health care Community-based Question Answering: A case study in alcoholism
In this study, we developed an algorithm to automatically answer health-related questions based on past questions and answers (QA).
Temporal Topic Analysis with Endogenous and Exogenous Processes
We consider the problem of modeling temporal textual data taking endogenous and exogenous processes into account.
Classification-based Financial Markets Prediction using Deep Neural Networks
Deep neural networks (DNNs) are powerful types of artificial neural networks (ANNs) that use several hidden layers.
Predictive Analytics Using Smartphone Sensors for Depressive Episodes
We first find the home location of a patient, which is then augmented with other sensor data to identify sleep patterns and select communication patterns.
Going Out of Business: Auction House Behavior in the Massively Multi-Player Online Game
The in-game economies of massively multi-player online games (MMOGs) are complex systems that have to be carefully designed and managed.
Semantic Properties of Customer Sentiment in Tweets
In addition to major findings, we apply LDA (Latent Dirichlet Allocations) to the same data and drew latent topics that represent consumers' positive opinions and negative opinions on social media.
Skill-Based Differences in Spatio-Temporal Team Behavior in Defence of The Ancients 2
Results indicate that spatio-temporal behavior of MOBA teams is related to team skill, with professional teams having smaller within-team distances and conducting more zone changes than amateur teams.
Evaluating the Performance of Offensive Linemen in the NFL
Using a variety of statistics related to an offensive lineman's performance, we develop a framework to objectively analyze the overall performance of an individual offensive lineman and determine specific linemen who are overvalued or undervalued relative to their salary.
Clustering Time-Series Energy Data from Smart Meters
Investigations have been performed into using clustering methods in data mining time-series data from smart meters.
Predicting litigation likelihood and time to litigation for patents
We develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation based on both textual and non-textual features.
