Education
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion Zhenheng T ang Y onggang Zhang Peijie Dong Yiu-ming Cheung Amelie Chi Zhou Bo Han
One-shot Federated Learning (OFL) significantly reduces communication costs in FL by aggregating trained models only once. However, the performance of advanced OFL methods is far behind the normal FL.
Emmanuel Abbe
Can Transformers predict new syllogisms by composing established ones?
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
In a single-agent setting, IL was shown to be done efficiently via an inverse soft-Q learning process.
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction Anton Rodomanov CISPA
Lipschitz gradient, without needing to know neither the corresponding Lipschitz constants, nor the oracle's variance but enjoying the rates which are characteristic for algorithms which have the
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement Zhehao Huang, Xinwen Cheng, JingHao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang Shanghai Jiao Tong University
However, computing the second-order Hessian for large-scale models is intractable.
UltraMedical: Building Specialized Generalists in Biomedicine
Exploring how to build open-source, GPT-4-level LLMs in the field of biomedicine is underway.
