← Authors

Jason Lee

87 papers · 2010–2025 · 13 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🌍 Conference Polyglot (13) πŸ—ΊοΈ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9) πŸƒ Academic Marathon (15) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🏠 Conference Loyalist (44) 🌟 Keyword Trendsetter Combo (5) 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown πŸ† Keyword Champion πŸ† Grand Slam πŸ”¬ Deep Specialist (29) ❓ The Questioner πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (14) ⚑ Prolific Year (11) πŸ’Ž Century Club (87) πŸ—ƒοΈ Keyword Collector (89)

Conferences

NIPS (44) ICML (13) AISTATS (9) COLT (7) EMNLP (5) ACL (2) AAAI (1) AACL (1) CORL (1) EACL (1) ICLR (1) IJCNLP (1) NAACL (1)

Top co-authors

Qi Lei (10) Kyunghyun Cho (7) Simon Du (6) Daniel Soudry (5) Alex Damian (5) Tengyu Ma (5) Bruce W. Lee (5) Suriya Gunasekar (5) Tianle Cai (4) Eshaan Nichani (4)

Research topics

Statistics (3) Applications (1) Education (1)

Keywords

gradient descent (21) sample complexity (11) neural network (10) representation learning (7) implicit bia (7) learning theory (6) neural tangent kernel (5) non-convex optimization (5) gradient flow (5) stochastic gradient descent (5) kernel methods (5) neural network optimization (4) function approximation (4) reinforcement learning (3) convergence guarantee (3) generalization bound (3) convex optimization (3) latent variable model (3) convergence rate (3) few-shot learning (3)

Papers

Anytime Acceleration of Gradient Descent COLT 2025
BranchOut: Capturing Realistic Multimodality in Autonomous Driving Decisions CORL 2025
REST: Retrieval-Based Speculative Decoding NAACL 2024
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding NIPS 2024
Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract) COLT 2024
A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification ACL 2023
LFTK: Handcrafted Features in Computational Linguistics ACL 2023
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability NIPS 2023
Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning NIPS 2023
Fine-Tuning Language Models with Just Forward Passes NIPS 2023
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms NIPS 2023
Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage NIPS 2023
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models NIPS 2023
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks NIPS 2023
Prompt-based Learning for Text Readability Assessment EACL 2023
Provable Hierarchy-Based Meta-Reinforcement Learning AISTATS 2023
Reconstructing Training Data from Model Gradient, Provably AISTATS 2023
Provably Efficient Reinforcement Learning via Surprise Bound AISTATS 2023
Offline Reinforcement Learning with Realizability and Single-policy Concentrability COLT 2022
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems NIPS 2022
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials NIPS 2022
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NIPS 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NIPS 2022
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent NIPS 2022
Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games AISTATS 2022
Optimization-Based Separations for Neural Networks COLT 2022
Neural Networks can Learn Representations with Gradient Descent COLT 2022
How Fine-Tuning Allows for Effective Meta-Learning NIPS 2021
Going Beyond Linear RL: Sample Efficient Neural Function Approximation NIPS 2021
Label Noise SGD Provably Prefers Flat Global Minimizers NIPS 2021
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization NIPS 2021
Shape Matters: Understanding the Implicit Bias of the Noise Covariance COLT 2021
How Important is the Train-Validation Split in Meta-Learning? ICML 2021
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks COLT 2021
A Theory of Label Propagation for Subpopulation Shift ICML 2021
Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021
Near-Optimal Linear Regression under Distribution Shift ICML 2021
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features EMNLP 2021
Predicting What You Already Know Helps: Provable Self-Supervised Learning NIPS 2021
Beyond Lazy Training for Over-parameterized Tensor Decomposition NIPS 2020
Generalized Leverage Score Sampling for Neural Networks NIPS 2020
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation EMNLP 2020
Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior AAAI 2020
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters NIPS 2020
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot NIPS 2020
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks NIPS 2020
LXPER Index 2.0: Improving Text Readability Assessment Model for L2 English Students in Korea AACL 2020
SGD Learns One-Layer Networks in WGANs ICML 2020
Optimal transport mapping via input convex neural networks ICML 2020
Towards Understanding Hierarchical Learning: Benefits of Neural Representations NIPS 2020
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NIPS 2020
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity NIPS 2020
On the Discrepancy between Density Estimation and Sequence Generation EMNLP 2020
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel NIPS 2019
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods NIPS 2019
Countering Language Drift via Visual Grounding IJCNLP 2019
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models ICML 2019
Gradient Descent Finds Global Minima of Deep Neural Networks ICML 2019
Convergence of Gradient Descent on Separable Data AISTATS 2019
Countering Language Drift via Visual Grounding EMNLP 2019
Neural Temporal-Difference Learning Converges to Global Optima NIPS 2019
Convergence of Adversarial Training in Overparametrized Neural Networks NIPS 2019
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks ICML 2018
Implicit Bias of Gradient Descent on Linear Convolutional Networks NIPS 2018
Provably Correct Automatic Sub-Differentiation for Qualified Programs NIPS 2018
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport NIPS 2018
Adding One Neuron Can Eliminate All Bad Local Minima NIPS 2018
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced NIPS 2018
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement EMNLP 2018
Emergent Translation in Multi-Agent Communication ICLR 2018
On the Power of Over-parametrization in Neural Networks with Quadratic Activation ICML 2018
Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima ICML 2018
Characterizing Implicit Bias in Terms of Optimization Geometry ICML 2018
On the Learnability of Fully-Connected Neural Networks AISTATS 2017
Black-box Importance Sampling AISTATS 2017
Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data AISTATS 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points NIPS 2017
A Kernelized Stein Discrepancy for Goodness-of-fit Tests ICML 2016
Matrix Completion has No Spurious Local Minimum NIPS 2016
Evaluating the statistical significance of biclusters NIPS 2015
Exact Post Model Selection Inference for Marginal Screening NIPS 2014
Scalable Methods for Nonnegative Matrix Factorizations of Near-separable Tall-and-skinny Matrices NIPS 2014
Using multiple samples to learn mixture models NIPS 2013
Structure Learning of Mixed Graphical Models AISTATS 2013
On model selection consistency of penalized M-estimators: a geometric theory NIPS 2013
Proximal Newton-type methods for convex optimization NIPS 2012
Practical Large-Scale Optimization for Max-norm Regularization NIPS 2010