11 papers
Exact Simulation of Multivariate Diffusions and Bridges
Jose Blanchet, Jikai Jin, Hao Liu
We provide the first generic exact sampling algorithms with finite expected total cost for uniformly elliptic multivariate diffusions and the corresponding diffusion bridges with b…
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
Junze Ye, Jiayi Cheng, Miao Lu +3
For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses…
Sobolev Regularized Score Difference Estimation in Diffusion Models
Chenghan Xie, Jose Blanchet, Renyuan Xu
Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise naturally in transfer learning, whe…
Robust Assortment Optimization from Observational Data
Miao Lu, Yuxuan Han, Han Zhong +2
Assortment optimization is a fundamental challenge in modern retail and recommendation systems, where the goal is to select a subset of products that maximizes expected revenue und…
Duality and Policy Evaluation in Distributionally Robust Bayesian Diffusion Control
Jose Blanchet, Jiayi Cheng, Yuewei Ling +2
We study diffusion control problems under parameter uncertainty. Controllers based on plug-in estimation can be brittle due to potential distribution shifts. Bayesian control with…
Learning an Optimal Assortment Policy under Observational Data
Yuxuan Han, Han Zhong, Miao Lu +2
We study the fundamental problem of offline assortment optimization under the Multinomial Logit (MNL) model, where sellers must determine the optimal subset of the products to offe…
ScoreFusion: Fusing Score-based Generative Models via Kullback-Leibler Barycenters
Hao Liu, Junze Tony Ye, Jose Blanchet +1
We introduce ScoreFusion, a theoretically grounded method for fusing multiple pre-trained diffusion models that are assumed to generate from auxiliary populations. ScoreFusion is p…
Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces
Shengbo Wang, Jason Meng, Nian Si +2
We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply cha…
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Zhihan Liu, Miao Lu, Shenao Zhang +5
Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to ou…
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
Miao Lu, Han Zhong, Tong Zhang +1
The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to…
On the Foundation of Distributionally Robust Reinforcement Learning
Shengbo Wang, Nian Si, Jose Blanchet +1
Motivated by the need for a robust policy in the face of environment shifts between training and deployment, we contribute to the theoretical foundation of distributionally robust…