Kefan Dong
13 papers · 2019–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (27) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze
🏆
Grand Slam
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(67)
Venues
Top co-authors
Research topics
Machine Learning
(11)
Optimization & Theory
(9)
Reinforcement Learning
(7)
Methods
(7)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types · Machine Learning
(5)
Mathematics & Optimization
(3)
Applications
(2)
Optimization
(2)
Deep Learning
(1)
Application Areas
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
neural network
(4)
sample complexity
(3)
reinforcement learning
(3)
online learning
(2)
minimax regret
(2)
multi-armed bandit
(2)
contextual bandit
(2)
model-based reinforcement learning
(2)
markov decision process
(2)
policy optimization
(1)
model-based learning
(1)
learning theory
(1)
formal verification
(1)
function approximation
(1)
model misspecification
(1)
offline reinforcement learning
(1)
batch learning
(1)
domain generalization
(1)
policy selection
(1)
gradient descent
(1)
Papers
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
ICML 2025
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making
ICLR 2023
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
NeurIPS 2023
First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
ICLR 2023
Model-Based Offline Reinforcement Learning with Local Misspecification
AAAI 2023
Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields
COLT 2023
Design of Experiments for Stochastic Contextual Linear Bandits
NeurIPS 2021
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
NeurIPS 2021
Multinomial Logit Bandit with Low Switching Cost
ICML 2020
On the Expressivity of Neural Networks for Deep Reinforcement Learning
ICML 2020
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
ICLR 2020
Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank
COLT 2020
Exploration via Hindsight Goal Generation
NeurIPS 2019