Zhihua Zhang

CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal AAAI 2026 On the Convergence of Projected Policy Gradient for Any Constant Step Sizes JMLR 2025 Statistical Efficiency of Distributional Temporal Difference Learning NIPS 2024 A Random Projection Approach to Personalized Federated Learning: Enhancing Communication Efficiency, Robustness, and Fairness JMLR 2024 Lower Complexity Bounds of Finite-Sum Optimization Problems: The Results and Construction JMLR 2024 Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes ICML 2023 A Statistical Analysis of Polyak-Ruppert Averaged Q-Learning AISTATS 2023 Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis NIPS 2023 Entropy-based Training Methods for Scalable Neural Implicit Samplers NIPS 2023 Enhancing Adversarial Robustness via Score-Based Optimization NIPS 2023 Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models NIPS 2023 MR-P: A Parallel Decoding Algorithm for Iterative Refinement Non-Autoregressive Translation ACL 2022 Federated Reinforcement Learning with Environment Heterogeneity AISTATS 2022 Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods JMLR 2022 On Non-local Convergence Analysis of Deep Linear Networks ICML 2022 A Statistical Online Inference Approach in Averaged Stochastic Approximation NIPS 2022 Semi-infinitely Constrained Markov Decision Processes NIPS 2022 Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness NIPS 2022 Asymptotic Behaviors of Projected Stochastic Approximation: A Jump Diffusion Perspective NIPS 2022 Con-NAT: Contrastive Non-autoregressive Neural Machine Translation EMNLP 2022 Statistical Estimation and Online Inference via Local SGD COLT 2022 Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence NIPS 2021 Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data NIPS 2021 Memory-Efficient Differentiable Transformer Architecture Search ACL 2021 Multi-split Reversible Transformers Can Enhance Neural Machine Translation EACL 2021 Communication-Efficient Distributed SVD via Local Power Iterations ICML 2021 Memory-Efficient Differentiable Transformer Architecture Search IJCNLP 2021 Approximate Newton Methods JMLR 2021 Nesterov's Acceleration for Approximate Newton JMLR 2020 Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems ICML 2020 Efficient Spectrum-Revealing CUR Matrix Decomposition AISTATS 2020 Train Once, and Decode As You Like COLING 2020 Active Learning Approaches to Enhancing Neural Machine Translation EMNLP 2020 Do Subsampled Newton Methods Work for High-Dimensional Data? AAAI 2020 On the Convergence of FedAvg on Non-IID Data ICLR 2020 A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning NIPS 2019 Robust Frequent Directions with Application in Online Learning JMLR 2019 Lipschitz Generative Adversarial Nets ICML 2019 CPSG-MCMC: Clustering-Based Preprocessing method for Stochastic Gradient MCMC AISTATS 2017 Approximate Newton Methods and Their Local Convergence ICML 2017 Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition JMLR 2016 ECNU at SemEval-2016 Task 5: Extracting Effective Features from Relevant Fragments in Sentence for Aspect-Based Sentiment Analysis in Reviews SEMEVAL 2016 Frequent Direction Algorithms for Approximate Matrix Multiplication with Applications in CCA IJCAI 2016 ECNU at SemEval-2016 Task 7: An Enhanced Supervised Learning Method for Lexicon Sentiment Intensity Ranking SEMEVAL 2016 ECNU at SemEval-2016 Task 4: An Empirical Investigation of Traditional NLP Features and Word Embedding Features for Sentence-level and Topic-level Sentiment Analysis in Twitter SEMEVAL 2016 SPSD Matrix Approximation vis Column Selection: Theories, Algorithms, and Extensions JMLR 2016 ECNU at SemEval 2016 Task 6: Relevant or Not? Supportive or Not? A Two-step Learning System for Automatic Detecting Stance in Tweets SEMEVAL 2016 ECNU: Multi-level Sentiment Analysis on Twitter Using Traditional Linguistic Features and Word Embedding Features SEMEVAL 2015 Support Matrix Machines ICML 2015 ECNU: Extracting Effective Features from Multiple Sequential Sentences for Target-dependent Sentiment Analysis in Reviews SEMEVAL 2015 A Scalable Community Detection Algorithm for Large Graphs Using Stochastic Block Models IJCAI 2015 ECNU: A Combination Method and Multiple Features for Aspect Extraction and Sentiment Polarity Classification SEMEVAL 2014 Distributed Power-law Graph Computing: Theoretical and Empirical Analysis NIPS 2014 Efficient Algorithms and Error Analysis for the Modified Nystrom Method AISTATS 2014 Making Fisher Discriminant Analysis Scalable ICML 2014 Nonconvex Relaxation Approaches to Robust Matrix Recovery IJCAI 2013 A Scalable Approach to Column-Based Low-Rank Matrix Approximation IJCAI 2013 Improving CUR Matrix Decomposition and the Nystrom Approximation via Adaptive Sampling JMLR 2013 EP-GIG Priors and Applications in Bayesian Sparse Learning JMLR 2012 A Scalable CUR Matrix Decomposition Algorithm: Lower Time Complexity and Tighter Bound NIPS 2012 Nonconvex Penalization Using Laplace Exponents and Concave Conjugates NIPS 2012 An Autoregressive Approach to Nonparametric Hierarchical Dependent Modeling AISTATS 2012 Coherence Functions with Applications in Large-Margin Classification Methods JMLR 2012 Bayesian Generalized Kernel Mixed Models JMLR 2011 Regularized Discriminant Analysis, Ridge Regression and Beyond JMLR 2010 Matrix-Variate Dirichlet Process Mixture Models AISTATS 2010 Bayesian Generalized Kernel Models AISTATS 2010 Probabilistic Relational PCA NIPS 2009 Optimal Scoring for Unsupervised Learning NIPS 2009 Posterior Consistency of the Silverman g-prior in Bayesian Model Choice NIPS 2008