Hyper-parameter Optimization for Federated Learning with Step-wise Adaptive Mechanismby Yasaman Saadati, M. Hadi AminiFirst submitted…
Coverage-Constrained Human-AI Cooperation with Multiple Expertsby Zheng Zhang, Cuong Nguyen, Kevin Wells, Thanh-Toan Do, David…
Aligning Few-Step Diffusion Models with Dense Reward Difference Learningby Ziyi Zhang, Li Shen, Sen Zhang,…
GROOT: Effective Design of Biological Sequences with Limited Experimental Databy Thanh V. T. Tran, Nhat…
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformersby Jake Grigsby, Justin Sasek, Samyak…
Don’t Be So Positive: Negative Step Sizes in Second-Order Methodsby Betty Shea, Mark SchmidtFirst submitted…
Mirror Descent on Reproducing Kernel Banach Spacesby Akash Kumar, Mikhail Belkin, Parthe PanditFirst submitted to…
Constrained Diffusion with Trust Samplingby William Huang, Yifeng Jiang, Tom Van Wouwe, C. Karen LiuFirst…
FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Methodby Yu Jiang, Chee Wei Tan, Kwok-Yan…
On Reductions and Representations of Learning Problems in Euclidean Spacesby Bogdan Chornomaz, Shay Moran, Tom…