Search Results for author:
Found 29 papers, 10 papers with code
Mobile AR Depth Estimation: Challenges & Prospects -- Extended Version
In this paper, we investigate the challenges and opportunities of achieving accurate metric depth estimation in mobile AR.
Carbon-Efficient Neural Architecture Search
This work presents a novel approach to neural architecture search (NAS) that aims to reduce energy costs and increase carbon efficiency during the model design process.
Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting
In many data-driven applications, collecting data from different sources is increasingly desirable for enhancing performance.
Multi-Camera Lighting Estimation for Photorealistic Front-Facing Mobile Augmented Reality
This lack of support can be attributed to the unique challenges of obtaining 360$^\circ$ HDR environment maps, an ideal format of lighting representation, from the front-facing camera and existing techniques.
LitAR: Visually Coherent Lighting for Mobile Augmented Reality
In this work, we present the design and implementation of a lighting reconstruction framework called LitAR that enables realistic and visually-coherent rendering.
Multi-objective Optimization by Learning Space Partitions
In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier.
Multi-objective Optimization by Learning Space Partition
In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier.
Xihe: A 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality
Centering the key idea of 3D vision, in this work, we design an edge-assisted framework called Xihe to provide mobile AR applications the ability to obtain accurate omnidirectional lighting estimation in real time.
Memory-Efficient Deep Learning Inference in Trusted Execution Environments
This study identifies and proposes techniques to alleviate two key bottlenecks to executing deep neural networks in trusted execution environments (TEEs): page thrashing during the execution of convolutional layers and the decryption of large weight matrices in fully-connected layers.
Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning
Further, we observe that Sync-Switch achieves 3. 8% higher converged accuracy with just 1. 23X the training time compared to training with ASP.
Few-shot Neural Architecture Search
supernet, to approximate the performance of every architecture in the search space via weight-sharing.
Temporal mixture ensemble models for intraday volume forecasting in cryptocurrency exchange markets
We study the problem of the intraday short-term volume forecasting in cryptocurrency exchange markets.
ESG2Risk: A Deep Learning Framework from ESG News to Stock Volatility Prediction
Incorporating environmental, social, and governance (ESG) considerations into systematic investments has drawn numerous attention recently.
Characterizing and Modeling Distributed Training with Transient Cloud GPU Servers
However, it is challenging to determine the appropriate cluster configuration---e. g., server type and number---for different training workloads while balancing the trade-offs in training time, cost, and model accuracy.
PointAR: Efficient Lighting Estimation for Mobile Augmented Reality
We propose an efficient lighting estimation pipeline that is suitable to run on modern mobile devices, with comparable resource complexities to state-of-the-art mobile deep learning models.
Perseus: Characterizing Performance and Cost of Multi-Tenant Serving for CNN Models
Leveraging Perseus, we evaluated the inference throughput and cost for serving various models and demonstrated that multi-tenant model serving led to up to 12% cost reduction.
Characterizing the Deep Neural Networks Inference Performance of Mobile Applications
The key idea of CNNSelect is to make inference speed and accuracy trade-offs at runtime using a set of CNN models.
Distributed, Parallel, and Cluster Computing Performance
Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices
Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy.
Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction.
Low-dimensional statistical manifold embedding of directed graphs
We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way.
Sensing Social Media Signals for Cryptocurrency News
The ability to track and monitor relevant and important news in real-time is of crucial interest in multiple industrial sectors.
Speeding up Deep Learning with Transient Servers
Distributed training frameworks, like TensorFlow, have been proposed as a means to reduce the training time of deep learning models by using a cluster of GPU servers.
Exploring the interpretability of LSTM neural networks over multi-variable data
In learning a predictive model over multivariate time series consisting of target and exogenous variables, the forecasting performance and interpretability of the model are both essential for deployment and uncovering knowledge behind the data.
Multi-variable LSTM neural network for autoregressive exogenous model
In this paper, we propose multi-variable LSTM capable of accurate forecasting and variable importance interpretation for time series with exogenous variables.
An interpretable LSTM neural network for autoregressive exogenous model
In this paper, we propose an interpretable LSTM recurrent neural network, i. e., multi-variable LSTM for time series with exogenous variables.
Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders
In this paper, we study the ability to make the short-term prediction of the exchange price fluctuations towards the United States dollar for the Bitcoin market.
Is Simple Better? Revisiting Non-linear Matrix Factorization for Learning Incomplete Ratings
Matrix factorization techniques have been widely used as a method for collaborative filtering for recommender systems.
Cloud-based or On-device: An Empirical Study of Mobile Deep Inference
To utilize these cloud-based models, mobile apps will have to send input data over the network.
Robust Online Time Series Prediction with Recurrent Neural Networks
Time series forecasting for streaming data plays an important role in many real applications, ranging from IoT systems, cyber-networks, to industrial systems and healthcare.
