Jason D. Lee

Learning Hierarchical Polynomials of Multiple Nonlinear Features ICLR 2025 Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow ICLR 2025 Understanding Optimization in Deep Learning with Central Flows ICLR 2025 Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization ICLR 2025 Understanding Factual Recall in Transformers via Associative Memories ICLR 2025 Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF ICLR 2025 Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding ICML 2025 How Well Can Transformers Emulate In-Context Newton’s Method? AISTATS 2025 Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback ICML 2025 Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation ICML 2025 Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025 Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought ICLR 2025 Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank ICLR 2025 Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads ICML 2024 Learning and Transferring Sparse Contextual Bigrams with Linear Transformers NIPS 2024 REBEL: Reinforcement Learning via Regressing Relative Rewards NIPS 2024 Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit NIPS 2024 Scaling Laws in Linear Regression: Compute, Parameters, and Data NIPS 2024 Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity NIPS 2024 Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking ICLR 2024 Learning Hierarchical Polynomials with Three-Layer Neural Networks ICLR 2024 Horizon-Free Regret for Linear Markov Decision Processes ICLR 2024 Provable Offline Preference-Based Reinforcement Learning ICLR 2024 Provable Reward-Agnostic Preference-Based Reinforcement Learning ICLR 2024 Teaching Arithmetic to Small Transformers ICLR 2024 Provably Efficient CVaR RL in Low-rank MDPs ICLR 2024 BitDelta: Your Fine-Tune May Only Be Worth One Bit NIPS 2024 LoRA Training in the NTK Regime has No Spurious Local Minima ICML 2024 An Information-Theoretic Analysis of In-Context Learning ICML 2024 How Transformers Learn Causal Structure with Gradient Descent ICML 2024 Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot ICML 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 Can We Find Nash Equilibria at a Linear Rate in Markov Games? ICLR 2023 Regret Guarantees for Online Deep Control L4DC 2023 PAC Reinforcement Learning for Predictive State Representations ICLR 2023 Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games ICLR 2023 Efficient displacement convex optimization with particle gradient descent ICML 2023 Looped Transformers as Programmable Computers ICML 2023 Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023 Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings ICML 2023 Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning ICML 2023 Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition AISTATS 2023 Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability ICLR 2023 Towards General Function Approximation in Zero-Sum Markov Games ICLR 2022 Few-Shot Learning via Learning the Representation, Provably ICLR 2021 On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift JMLR 2021 Impact of Representation Learning in Linear Bandits ICLR 2021 Kernel and Rich Regimes in Overparametrized Models COLT 2020 Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks ICLR 2020 When is a Convolutional Filter Easy to Learn? ICLR 2018 Learning One-hidden-layer Neural Networks with Landscape Design ICLR 2018 Communication-efficient Sparse Regression JMLR 2017 Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement JMLR 2017 Gradient Descent Only Converges to Minimizers COLT 2016 L1-regularized Neural Networks are Improperly Learnable in Polynomial Time ICML 2016 Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares JMLR 2015