Yunzong Xu
4 papers · 2019–2022 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
COLT (2)
ICML (1)
NIPS (1)
Top co-authors
Keywords
phase transition
(2)
online learning
(1)
function approximation
(1)
sample complexity
(1)
regret minimization
(1)
value function approximation
(1)
stochastic process
(1)
optimal regret
(1)
multi-armed bandit
(1)
regret bound
(1)
online algorithm
(1)
contextual bandit
(1)
stochastic bandit
(1)
switching cost
(1)
dynamic pricing
(1)
instance-dependent regret
(1)
offline datum
(1)
switching constraint
(1)
offline reinforcement learning
(1)
gap-dependent complexity
(1)
Papers
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
COLT 2022
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
COLT 2021
Online Pricing with Offline Data: Phase Transition and Inverse Square Law
ICML 2020
Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints
NIPS 2019