Audrey Huang
13 papers · 2019–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (7)
🏃
Academic Marathon
(6)
🧭
Keyword Pioneer
🏆
Keyword Champion
(2)
🔥
Unstoppable
(5)
💎
Century Club
(13)
❓
The Questioner
🗃️
Keyword Collector
(51)
Conferences
ICML (3)
NIPS (3)
AISTATS (2)
COLT (2)
ICLR (2)
CORL (1)
Top co-authors
Keywords
sample complexity
(3)
off-policy evaluation
(3)
offline reinforcement learning
(3)
value function
(2)
risk assessment
(2)
doubly robust estimator
(2)
conditional value at risk
(2)
cumulative distribution function
(2)
density ratio
(2)
gradient-based optimization
(1)
importance sampling
(1)
markov decision process
(1)
optimal control
(1)
function approximation
(1)
empirical risk minimization
(1)
gradient estimation
(1)
policy gradient
(1)
sampling efficiency
(1)
spatial configuration
(1)
primal-dual algorithm
(1)
Papers
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract)
COLT 2025
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
ICLR 2025
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
ICML 2025
Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
NIPS 2024
Timing as an Action: Learning When to Observe and Act
AISTATS 2024
Reinforcement Learning in Low-rank MDPs with Density Features
ICML 2023
Offline Reinforcement Learning with Realizability and Single-policy Concentrability
COLT 2022
Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions
NIPS 2022
Off-Policy Risk Assessment for Markov Decision Processes
AISTATS 2022
Supervised Learning with General Risk Functionals
ICML 2022
Off-Policy Risk Assessment in Contextual Bandits
NIPS 2021
Graph-Structured Visual Imitation
CORL 2019