Deep Learning
Why Transformers Need Adam: A Hessian Perspective
CNNs, MLPs, and quadratic problems, and find that SGD can perform on par with Adam on problems without block heterogeneity, but performs worse than Adam when the heterogeneity exists.
Learning Bregman Divergences with Application to Robustness
Image similarity measures are also crucial in the field of robust machine learning.
Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks Shuai He
Assessment (IEA) is now being accorded serious attention.
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
This paper presents an auditing procedure for the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm in the black-box threat model that is substantially tighter than prior work.
Parallelizing Model-based Reinforcement Learning Over the Sequence Length
Recently, Model-based Reinforcement Learning (MBRL) methods have demonstrated stunning sample efficiency in various RL domains.