3 papers
cs.LG2026
Wasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition
Chencheng Tang, Xuanyu Xue, Fangyikang Wang +2
Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Motivated by privacy and scalabilit…
cs.LG2026
Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting
Federico Zucchi, Yi Xie, Chao Zhang +3
Adaptive patching is a recent and compelling proposal for time-series Transformers: allocate finer patches where the sequence looks locally informative. This paper asks under what…
cs.LG2024
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Wensong Bai, Chao Zhang, Yichao Fu +3
In this paper, we propose the first fully push-forward-based distributional reinforcement learning algorithm, named PACER, which consists of a distributional critic, a stochastic a…