9 papers
Conditional Flow Models for Offline Maximum Entropy Reinforcement Learning
Hao Cheng, Yuling Jiao, Lican Kang +2
Offline maximum entropy reinforcement learning seeks to estimate the optimal soft action-value function \(Q^*\) from a fixed dataset without further interaction with the environmen…
Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics
Yuling Jiao, Lican Kang, Jerry Zhijian Yang +2
Gaussian diffusion models offer a practical framework for generative modeling. Denoising Lévy Probabilistic Models (DLPM) introduce heavy-tailed perturbations with a fixed tail ind…
Lesion-Aware Attention for Mammography Segmentation with Heterogeneous Supervision
Di Dai, Bo Liu, Liwei Wang
Accurate lesion segmentation in mammography is important for computer-aided breast cancer diagnosis, but dense pixel-level annotations remain costly and limited. Existing public se…
Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem
Rasul Khanbayov, Hasan Kurban
Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can be. We observe that almost ever…
Deep Weighted Bellman Residual Minimization for Estimation
Lican Kang, Jerry Zhijian Yang, Cheng Yuan +1
Off-policy evaluation is a foundational component of offline reinforcement learning, aiming to assess and optimize policy performance using pre-collected datasets. However, such da…
Schrödinger--Föllmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis
Yuling Jiao, Lican Kang, Jerry Zhijian Yang +1
Diffusion policies represent multimodal action distributions, but an advantage-weighted update does not specify how to sample from the resulting target distribution. We propose Sch…
Offline Deep Q* Estimation with Diffusion Models
Xiaohong Chen, Yuling Jiao, Lican Kang +2
In offline RL, estimating the optimal action-value function can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental chal…
Conditional Diffusion for Nonparametric Instrumental Variable Quantile Regression
Xingdong Feng, Xinhong Jiang, Yuling Jiao +2
This work proposes deep nonparametric Instrumental variable quantile regression (IVQR), a two-stage estimator that combines conditional diffusion modeling with a kernel-smoothed co…
Deep Bootstrap
Jinyuan Chang, Yuling Jiao, Lican Kang +1
In this work, we propose a novel deep bootstrap framework for nonparametric regression based on conditional diffusion models. Specifically, we construct a conditional diffusion mod…