← Authors

Simon S Du

39 papers · 2016–2024 · 2 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (68) 🌍 Conference Polyglot (2) πŸƒ Academic Marathon (8) 🏠 Conference Loyalist (37) πŸ”¬ Deep Specialist (13) πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (189) ⚑ Prolific Year (6) πŸ’Ž Century Club (39) πŸ”₯ Unstoppable (9) πŸ“ˆ Trend Setter ❓ The Questioner (3)

Conferences

NIPS (37) COLT (2)

Top co-authors

Ruosong Wang (8) Qiwen Cui (6) Simon S. Du (5) Ruslan Salakhutdinov (5) Lin Yang (4) Maryam Fazel (4) BarnabΓ‘s PΓ³czos (4) Aarti Singh (4) Michael I. Jordan (3) Yifang Chen (3)

Keywords

sample complexity (14) gradient descent (6) markov decision process (6) regret bound (5) reinforcement learning (4) offline reinforcement learning (4) representation learning (3) nash equilibrium (3) non-convex optimization (3) markov game (3) multi-agent system (3) robust optimization (2) linear function approximation (2) multi-task learning (2) optimal policy (2) active learning (2) global convergence (2) neural tangent kernel (2) matrix factorization (2) multi-agent reinforcement learning (2)

Papers

Understanding the Gains from Repeated Self-Distillation NIPS 2024
Settling the sample complexity of online reinforcement learning COLT 2024
Optimal Multi-Distribution Learning COLT 2024
Learning Optimal Tax Design in Nonatomic Congestion Games NIPS 2024
Learning to Cooperate with Humans using Generative Agents NIPS 2024
Decoding-Time Language Model Alignment with Multiple Objectives NIPS 2024
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models NIPS 2024
Active representation learning for general task space with applications in robotics NIPS 2023
Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NIPS 2023
A Reduction-based Framework for Sequential Decision Making with Delayed Feedback NIPS 2023
Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure NIPS 2023
Learning in Congestion Games with Bandit Feedback NIPS 2022
When are Offline Two-Player Zero-Sum Markov Games Solvable? NIPS 2022
On Gap-dependent Bounds for Offline Reinforcement Learning NIPS 2022
Near-Optimal Randomized Exploration for Tabular Markov Decision Processes NIPS 2022
Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus NIPS 2022
Provable General Function Class Representation Learning in Multitask Bandits and MDP NIPS 2022
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NIPS 2021
Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization NIPS 2021
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP NIPS 2021
Nearly Horizon-Free Offline Reinforcement Learning NIPS 2021
Corruption Robust Active Learning NIPS 2021
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NIPS 2020
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning NIPS 2020
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity NIPS 2020
On Reward-Free Reinforcement Learning with Linear Function Approximation NIPS 2020
Planning with General Objective Functions: Going Beyond Total Rewards NIPS 2020
Is Long Horizon RL More Difficult Than Short Horizon RL? NIPS 2020
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels NIPS 2019
On Exact Computation with an Infinitely Wide Neural Net NIPS 2019
Acceleration via Symplectic Discretization of High-Resolution Differential Equations NIPS 2019
Towards Understanding the Importance of Shortcut Connections in Residual Networks NIPS 2019
Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle NIPS 2019
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced NIPS 2018
How Many Samples are Needed to Estimate a Convolutional Neural Network? NIPS 2018
Hypothesis Transfer Learning via Transformation Functions NIPS 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points NIPS 2017
On the Power of Truncated SVD for General High-rank Matrix Estimation Problems NIPS 2017
Efficient Nonparametric Smoothness Estimation NIPS 2016