Yingbin Liang

Theory on Mixture-of-Experts in Continual Learning ICLR 2025 Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers ICLR 2025 Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis JMLR 2025 A Theoretical Analysis of Self-Supervised Learning for Vision Transformers ICLR 2025 DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity ICLR 2025 Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach ICLR 2025 Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow ICLR 2025 How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias ICML 2025 Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective ICML 2025 Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining ICLR 2025 Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes ICLR 2024 On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback ICLR 2024 In-context Convergence of Transformers ICML 2024 Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NIPS 2024 Non-asymptotic Convergence of Training Transformers for Next-token Prediction NIPS 2024 In-Context Learning with Representations: Contextual Generalization of Trained Transformers NIPS 2024 Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games ICML 2024 Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK JMLR 2024 Sample Complexity Characterization for Linear Contextual MDPs AISTATS 2024 Doubly Robust Instance-Reweighted Adversarial Training ICLR 2024 Provably Efficient UCB-type Algorithms For Learning Predictive State Representations ICLR 2024 Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL ICLR 2023 M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation ICLR 2023 Non-stationary Reinforcement Learning under General Function Approximation ICML 2023 Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs ICLR 2023 Lower Bounds and Accelerated Algorithms for Bilevel Optimization JMLR 2023 Learning to Generalize Provably in Learning to Optimize AISTATS 2023 Near-Optimal Adversarial Reinforcement Learning with Switching Costs ICLR 2023 Online Nonconvex Optimization with Limited Instantaneous Oracle Feedback COLT 2023 Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization ICML 2023 Provably Efficient Algorithm for Nonstationary Low-Rank MDPs NIPS 2023 Non-Convex Bilevel Optimization with Time-Varying Objective Functions NIPS 2023 Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning ICLR 2023 Global Convergence of Two-Timescale Actor-Critic for Solving Linear Quadratic Regulator AAAI 2023 A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints ICML 2023 Theory on Forgetting and Generalization of Continual Learning ICML 2023 Will Bilevel Optimizers Benefit from Loops NIPS 2022 PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method ICLR 2022 Data sampling affects the complexity of online SGD over dependent data UAI 2022 Deterministic policy gradient: Convergence analysis UAI 2022 Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning JMLR 2022 Model-Based Offline Meta-Reinforcement Learning with Regularization ICLR 2022 On the Convergence Theory for Hessian-Free Bilevel Algorithms NIPS 2022 A Unifying Framework of Off-Policy General Value Function Evaluation NIPS 2022 Provable Generalization of Overparameterized Meta-learning Trained with SGD NIPS 2022 Provable Benefit of Multitask Representation Learning in Reinforcement Learning NIPS 2022 Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality ICML 2021 Faster Non-asymptotic Convergence for Double Q-learning NIPS 2021 Provably Faster Algorithms for Bilevel Optimization NIPS 2021 Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling AAAI 2021 Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms AISTATS 2021 When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence AISTATS 2021 Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry ICLR 2021 Bilevel Optimization: Convergence Analysis and Enhanced Design ICML 2021 CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee ICML 2021 Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters NIPS 2020 Finite-Time Analysis for Double Q-learning NIPS 2020 Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack AAAI 2020 History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms ICML 2020 Spectral Algorithms for Community Detection in Directed Networks JMLR 2020 Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent IJCAI 2020 Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization IJCAI 2020 Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms NIPS 2020 Reanalysis of Variance Reduced Temporal Difference Learning ICLR 2020 SGD Converges to Global Minimum in Deep Learning via Star-convex Path ICLR 2019 Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization ICML 2019 Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization AISTATS 2019 Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples NIPS 2019 Finite-Sample Analysis for SARSA with Linear Function Approximation NIPS 2019 SpiderBoost and Momentum: Faster Variance Reduction Algorithms NIPS 2019 Cubic Regularization with Momentum for Nonconvex Optimization UAI 2019 Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties ICLR 2018 Distributed Proximal Gradient Algorithm for Partially Asynchronous Computer Clusters JMLR 2018 Convergence of Cubic Regularization for Nonconvex Optimization under KL Property NIPS 2018 Minimax Estimation of Neural Net Distance NIPS 2018 Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization ICML 2017 A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms JMLR 2017 Reshaped Wirtinger Flow for Solving Quadratic System of Equations NIPS 2016 Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow ICML 2016 On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System AISTATS 2016 Analysis of Robust PCA via Local Incoherence NIPS 2015 Block Regularized Lasso for Multivariate Multi-Response Linear Regression AISTATS 2013