Ji Liu

Dacheng Tao

IEEE Trans. Pattern Anal. Mach. Intell., 2022

PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2022

Data Poisoning Attacks on Federated Machine Learning.

[BibT_eX]

[DOI]

IEEE Internet Things J., 2022

Stochastic Gradient Descent without Full Data Shuffle.

[BibT_eX]

[DOI]

CoRR, 2022

E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles.

[BibT_eX]

[DOI]

CoRR, 2022

LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction.

[BibT_eX]

[DOI]

CoRR, 2022

Adversarial Contrastive Self-Supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Prototype Feature Extraction for Multi-task Learning.

[BibT_eX]

[DOI]

Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022

In-Database Machine Learning with CorgiPile: Stochastic Gradient Descent without Full Data Shuffle.

[BibT_eX]

[DOI]

Proceedings of the SIGMOD '22: International Conference on Management of Data, Philadelphia, PA, USA, June 12, 2022

Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters.

[BibT_eX]

[DOI]

Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Unified Visual Transformer Compression.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Progressive Teacher-Student Training Framework for Music Tagging.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

BAGUA: Scaling up Distributed Learning with System Relaxations.

[BibT_eX]

[DOI]

Proc. VLDB Endow., 2021

Shifted Chunk Transformer for Spatio-Temporal Representational Learning.

[BibT_eX]

[DOI]

CoRR, 2021

PASTO: Strategic Parameter Optimization in Recommendation Systems - Probabilistic is Better than Deterministic.

[BibT_eX]

[DOI]

CoRR, 2021

POSO: Personalized Cold Start Modules for Large-scale Recommender Systems.

[BibT_eX]

[DOI]

CoRR, 2021

Shifted Chunk Transformer for Spatio-Temporal Representational Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

ErrorCompensatedX: error compensation for variance reduced algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Purify and Generate: Learning Faithful Item-to-Item Graph from Noisy User-Item Interaction Behaviors.

[BibT_eX]

[DOI]

Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

UMEC: Unified model and embedding compression for efficient recommendation systems.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Hand Image Understanding via Deep Multi-Task Learning.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from Audio Stream.

[BibT_eX]

[DOI]

Proceedings of the ICBDT 2021: 4th International Conference on Big Data Technologies, Zibo, China, September 24, 2021

E2VTS: Energy-Efficient Video Text Spotting From Unmanned Aerial Vehicles.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

SpeechNAS: Towards Better Trade-Off Between Latency and Accuracy for Large-Scale Speaker Verification.

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

The 2020 Low-Power Computer Vision Challenge.

[BibT_eX]

[DOI]

Proceedings of the 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2021

2020

Hierarchical Prototype Learning for Zero-Shot Recognition.

[BibT_eX]

[DOI]

IEEE Trans. Multim., 2020

Learning Simple Thresholded Features With Sparse Support Recovery.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., 2020

Distributed Learning Systems with First-Order Methods.

[BibT_eX]

[DOI]

Ce Zhang

Found. Trends Databases, 2020

Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach.

[BibT_eX]

[DOI]

CoRR, 2020

Themes Inferred Audio-visual Correspondence Learning.

[BibT_eX]

[DOI]

CoRR, 2020

APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm.

[BibT_eX]

[DOI]

CoRR, 2020

Lossless CNN Channel Pruning via Gradient Resetting and Convolutional Re-parameterization.

[BibT_eX]

[DOI]

CoRR, 2020

Finite-Sample Analysis of GTD Algorithms.

[BibT_eX]

[DOI]

CoRR, 2020

Data Poisoning Attacks on Federated Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2020

End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines.

[BibT_eX]

[DOI]

CoRR, 2020

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

HOT-Net: Non-Autoregressive Transformer for 3D Hand-Object Pose Estimation.

[BibT_eX]

[DOI]

Proceedings of the MM '20: The 28th ACM International Conference on Multimedia, 2020

GAN Slimming: All-in-One GAN Compression by a Unified Optimization Framework.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Seeing All From a Few: ℓ<sub>1</sub>-Norm-Induced Discriminative Prototype Selection.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2019

A Robust AUC Maximization Framework With Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2019

Dualityfree Methods for Stochastic Composition Optimization.

[BibT_eX]

[DOI]

Liu Liu

Dacheng Tao

IEEE Trans. Neural Networks Learn. Syst., 2019

Lifelong Metric Learning.

[BibT_eX]

[DOI]

IEEE Trans. Cybern., 2019

Anomaly detection via adaptive greedy model.

[BibT_eX]

[DOI]

Neurocomputing, 2019

Stochastic Recursive Variance Reduction for Efficient Smooth Non-Convex Compositional Optimization.

[BibT_eX]

[DOI]

Huizhuo Yuan

CoRR, 2019

ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries.

[BibT_eX]

[DOI]

CoRR, 2019

Learning Sparsity and Quantization Jointly and Automatically for Neural Network Compression via Constrained Optimization.

[BibT_eX]

[DOI]

CoRR, 2019

Central Server Free Federated Learning over Single-sided Trust Social Networks.

[BibT_eX]

[DOI]

CoRR, 2019

DeepSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression.

[BibT_eX]

[DOI]

CoRR, 2019

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression.

[BibT_eX]

[DOI]

CoRR, 2019

Adversarially Trained Model Compression: When Robustness Meets Efficiency.

[BibT_eX]

[DOI]

CoRR, 2019

Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Model Compression with Adversarial Robustness: A Unified Optimization Framework.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Distributed Learning over Unreliable Networks.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

A Generic Active Learning Framework for Class Imbalance Applications.

[BibT_eX]

[DOI]

Aditya R. Bhattacharya

Shayok Chakraborty

Proceedings of the 30th British Machine Vision Conference 2019, 2019

AutoML from Service Provider's Perspective: Multi-device, Multi-tenant Model Selection with GP-EI.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Revisit Batch Normalization: New Understanding and Refinement via Composition Optimization.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Online Similarity Learning for Big Data with Overfitting.

[BibT_eX]

[DOI]

IEEE Trans. Big Data, 2018

Optimal Expert Knowledge Elicitation for Bayesian Network Structure Identification.

[BibT_eX]

[DOI]

IEEE Trans Autom. Sci. Eng., 2018

Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads.

[BibT_eX]

[DOI]

Proc. VLDB Endow., 2018

Ease.ml in Action: Towards Multi-tenant Declarative Learning Services.

[BibT_eX]

[DOI]

Proc. VLDB Endow., 2018

User attribute discovery with missing labels.

[BibT_eX]

[DOI]

Pattern Recognit., 2018

Switching-State Dynamical Modeling of Daily Behavioral Data.

[BibT_eX]

[DOI]

J. Heal. Informatics Res., 2018

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2018

ECC: Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model.

[BibT_eX]

[DOI]

CoRR, 2018

P-MCGS: Parallel Monte Carlo Acyclic Graph Search.

[BibT_eX]

[DOI]

CoRR, 2018

Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization.

[BibT_eX]

[DOI]

CoRR, 2018

Proximal Online Gradient is Optimum for Dynamic Regret.

[BibT_eX]

[DOI]

Yawei Zhao

Shuang Qiu

CoRR, 2018

Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem.

[BibT_eX]

[DOI]

CoRR, 2018

Marginal Policy Gradients for Complex Control.

[BibT_eX]

[DOI]

CoRR, 2018

End-to-End Learning of Energy-Constrained Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2018

GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2018

A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification.

[BibT_eX]

[DOI]

CoRR, 2018

Multi-device, Multi-tenant Model Selection with GP-EI.

[BibT_eX]

[DOI]

CoRR, 2018

Decentralization Meets Quantization.

[BibT_eX]

[DOI]

CoRR, 2018

Communication Compression for Decentralized Training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

D<sup>2</sup>: Decentralized Training over Decentralized Data.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Asynchronous Decentralized Parallel Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Adaptive Greedy Dictionary Selection for Web Media Summarization.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2017

Prognostics of surgical site infections using dynamic health data.

[BibT_eX]

[DOI]

J. Biomed. Informatics, 2017

CHI: A contemporaneous health index for degenerative disease monitoring using longitudinal measurements.

[BibT_eX]

[DOI]

J. Biomed. Informatics, 2017

Duality-free Methods for Stochastic Composition Optimization.

[BibT_eX]

[DOI]

Liu Liu

Dacheng Tao

CoRR, 2017

Lifelong Metric Learning.

[BibT_eX]

[DOI]

CoRR, 2017

A scalable algorithm for structure identification of complex gene regulatory network from temporal expression data.

[BibT_eX]

[DOI]

BMC Bioinform., 2017

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

On The Projection Operator to A Three-view Cardinality Constrained Set.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Transformed Anti-Sparse Hashing.

[BibT_eX]

[DOI]

Proceedings of the British Machine Vision Conference 2017, 2017

Finite-sum Composition Optimization via Variance Reduced Gradient Descent.

[BibT_eX]

[DOI]

Mengdi Wang

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

An accelerated randomized Kaczmarz algorithm.

[BibT_eX]

[DOI]

Math. Comput., 2016

ZipML: An End-to-end Bitwise Framework for Dense Generalized Linear Models.

[BibT_eX]

[DOI]

CoRR, 2016

Asynchronous Parallel Greedy Coordinate Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Online Feature Selection: A Limited-Memory Substitution Algorithm and Its Asynchronous Parallel Variation.

[BibT_eX]

[DOI]

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016

Staleness-Aware Async-SGD for Distributed Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

Proximal Gradient Temporal Difference Learning Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

On Benefits of Selection Diversity via Bilevel Exclusive Sparsity.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Privacy-CNH: A Framework to Detect Photo Privacy with Convolutional Neural Network using Hierarchical Features.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

Uncorrelated Group LASSO.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015

Speeded Up Low-Rank Online Metric Learning for Object Tracking.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., 2015

Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties.

[BibT_eX]

[DOI]

SIAM J. Optim., 2015

Deep sparse feature selection for computer aided endoscopy diagnosis.

[BibT_eX]

[DOI]

Pattern Recognit., 2015

An asynchronous parallel stochastic coordinate descent algorithm.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2015

Exclusive Sparsity Norm Minimization with Random Groups via Cone Projection.

[BibT_eX]

[DOI]

Yijun Huang

Mohammad Iftekhar Tanveer

CoRR, 2015

Finite-Sample Analysis of Proximal Gradient TD Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Unsupervised Extraction of Human-Interpretable Nonverbal Behavioral Cues in a Public Speaking Scenario.

[BibT_eX]

[DOI]

Mohammed (Ehsan) Hoque

Proceedings of the 23rd Annual ACM Conference on Multimedia Conference, MM '15, Brisbane, Australia, October 26, 2015

2014

Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces.

[BibT_eX]

[DOI]

CoRR, 2014

An Asynchronous Parallel Randomized Kaczmarz Algorithm.

[BibT_eX]

[DOI]

Srikrishna Sridhar

CoRR, 2014

Exclusive Feature Learning on Arbitrary Structures via \ell_{1, 2}-norm.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Forward-Backward Greedy Algorithms for General Convex Smooth Functions over A Cardinality Constraint.

[BibT_eX]

[DOI]

Ryohei Fujimaki

Proceedings of the 31th International Conference on Machine Learning, 2014

Spectral Clustering with a Convex Regularizer on Millions of Images.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2014, 2014

Low-Rank Online Metric Learning.

[BibT_eX]

[DOI]

Proceedings of the Low-Rank and Sparse Modeling for Visual Analysis, 2014

2013

Self-Supervised Online Metric Learning With Low Rank Constraint for Scene Categorization.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2013

Abnormal event detection in crowded scenes using sparse representation.

[BibT_eX]

[DOI]

Yang Cong

Junsong Yuan

Pattern Recognit., 2013

Tensor Completion for Estimating Missing Values in Visual Data.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2013

An Approximate, Efficient Solver for LP Rounding.

[BibT_eX]

[DOI]

CoRR, 2013

An Approximate, Efficient LP Solver for LP Rounding.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Guaranteed Sparse Recovery under Linear Transformation.

[BibT_eX]

[DOI]

Lei Yuan

Proceedings of the 30th International Conference on Machine Learning, 2013

2012

Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks.

[BibT_eX]

[DOI]

Jianhui Chen

ACM Trans. Knowl. Discov. Data, 2012

Sparse non-negative tensor factorization using columnwise coordinate descent.

[BibT_eX]

[DOI]

Pattern Recognit., 2012

A Multi-Stage Framework for Dantzig Selector and LASSO.

[BibT_eX]

[DOI]

Peter Wonka

J. Mach. Learn. Res., 2012

Robust Dequantized Compressive Sensing

[BibT_eX]

[DOI]

CoRR, 2012

Regularized Off-Policy TD-Learning.

[BibT_eX]

[DOI]

Bo Liu

Sridhar Mahadevan

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

2011

Sparse reconstruction cost for abnormal event detection.

[BibT_eX]

[DOI]

Yang Cong

Junsong Yuan

Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

2010

Multi-Stage Dantzig Selector.

[BibT_eX]

[DOI]

Peter Wonka