12 papers
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
Haichen Hu, Yuheng Zhang, David Simchi-Levi
Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can also transfer the teacher's sys…
Sharp Structure-Agnostic Minimax Risk for Partial Linear Models
Haichen Hu, David Simchi-Levi
We characterize the sharp structure-agnostic minimax risk for coefficient estimation in the partial linear model when the outcome and treatment nuisances are learned by two distinc…
Simultaneous Pointwise Majorization for Mixed Tail Processes with Applications in Gaussian Chaos and Ergodic Diffusions
Haichen Hu, David Simchi-Levi
Classical chaining controls an indexed stochastic process through a single worst-case bound and can therefore obscure substantial variation across the index set. We develop the fir…
Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles
Haichen Hu, David Simchi-Levi
Stochastic nonconvex optimization is central to training deep networks and LLMs in modern machine learning. We give a black-box reduction from stochastic nonconvex optimization to…
Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation
Haichen Hu, Jian Qian, David Simchi-Levi
Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls…
Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors
Haichen Hu, David Simchi-Levi
We study the problem of evaluating the excess risk of large-scale empirical risk minimization under the square loss. Leveraging the idea of wild refitting and resampling, we assume…
Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors
Haichen Hu, David Simchi-Levi
We study the problem of excess risk evaluation for empirical risk minimization (ERM) under convex losses. We show that by leveraging the idea of wild refitting, one can upper bound…
Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses
Haichen Hu, David Simchi-Levi
We study the excess risk evaluation of classical penalized empirical risk minimization (ERM) with Bregman losses. We show that by leveraging the idea of wild refitting, one can eff…
Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective
Haichen Hu, David Simchi-Levi
We study a sequential contextual decision-making problem in which certain covariates are missing but can be imputed using a pre-trained AI model. From a theoretical perspective, we…
Eluder-Dimension-Free Regret for Stage-Wise Constrained Contextual Bandits via Offline Regression
Haichen Hu, David Simchi-Levi, Navid Azizan
Contextual bandits with stage-wise constraints model decisions that must control risk while learning from their outcomes. We study this problem when only the selected action's rewa…
Contextual Online Decision Making with Infinite-Dimensional Functional Regression
Haichen Hu, Rui Ai, Stephen Bates +1
Contextual sequential decision-making problems play a crucial role in machine learning, encompassing a wide range of downstream applications such as bandits, sequential hypothesis…
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
Jian Qian, Haichen Hu, David Simchi-Levi
Motivated by the recent discovery of a statistical and computational reduction from contextual bandits to offline regression (Simchi-Levi and Xu, 2021), we address the general (sto…