Simon S. Du
17 papers · 2017–2024 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (7)
🐣
Hot Topic Early Bird
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(8)
🗃️
Keyword Collector
(70)
⚡
Prolific Year
(6)
🚀
Conference Pioneer
💎
Century Club
(17)
🔥
Unstoppable
(5)
❓
The Questioner
(4)
Conferences
ICLR (5)
NIPS (5)
COLT (2)
AISTATS (1)
ICML (1)
IJCAI (1)
JMLR (1)
UAI (1)
Top co-authors
Keywords
convergence rate
(2)
linear regression
(2)
linear function approximation
(2)
multi-agent reinforcement learning
(2)
game theory
(1)
principal component analysis
(1)
reinforcement learning
(1)
uncertainty quantification
(1)
convex optimization
(1)
preference learning
(1)
knowledge distillation
(1)
global convergence
(1)
expectation maximization
(1)
sparse estimation
(1)
language model alignment
(1)
particle filtering
(1)
model merging
(1)
covariance estimation
(1)
markov chain monte carlo
(1)
model architecture
(1)
Papers
Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract)
COLT 2024
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
NIPS 2024
Decoding-Time Language Model Alignment with Multiple Objectives
NIPS 2024
Learning to Cooperate with Humans using Generative Agents
NIPS 2024
Learning Optimal Tax Design in Nonatomic Congestion Games
NIPS 2024
Understanding the Gains from Repeated Self-Distillation
NIPS 2024
When is particle filtering efficient for planning in partially observed linear dynamical systems?
UAI 2021
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
ICLR 2020
DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs
IJCAI 2020
On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics
JMLR 2020
What Can Neural Networks Reason About?
ICLR 2020
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
ICLR 2020
Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity
AISTATS 2019
Gradient Descent Provably Optimizes Over-parameterized Neural Networks
ICLR 2019
When is a Convolutional Filter Easy to Learn?
ICLR 2018
Stochastic Variance Reduction Methods for Policy Evaluation
ICML 2017
Computationally Efficient Robust Sparse Estimation in High Dimensions
COLT 2017