9 citations · 20 across the 8 of their papers we have counts for
6 papers · 1 filter
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang +3
In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing…
FedLion: Faster Adaptive Federated Optimization with Fewer Communication
Zhiwei Tang, Tsung-Hui Chang
In Federated Learning (FL), a framework to train machine learning models across distributed data, well-known algorithms like FedAvg tend to have slow convergence rates, resulting i…
Accelerating Parallel Sampling of Diffusion Models
Zhiwei Tang, Jiasheng Tang, Hao Luo +2
Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent auto…
Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
Zhiwei Tang, Dmitry Rybin, Tsung-Hui Chang
In this study, we delve into an emerging optimization challenge involving a black-box objective function that can only be gauged via a ranking oracle-a situation frequently encount…
-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning
Zhiwei Tang, Yanmeng Wang, Tsung-Hui Chang
Federated Learning (FL) is a promising privacy-preserving distributed learning paradigm but suffers from high communication cost when training large-scale machine learning models.…
Low-rank Matrix Recovery With Unknown Correspondence
Zhiwei Tang, Tsung-Hui Chang, Xiaojing Ye +1
We study a matrix recovery problem with unknown correspondence: given the observation matrix , where is an unknown permutation matrix, we aim to reco…