Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningby Alexander Politowicz, Sahisnu Mazumder,…
Optimal Multiclass U-Calibration Error and Beyondby Haipeng Luo, Spandan Senapati, Vatsal SharanFirst submitted to arxiv…
Learning Human-Aligned Representations with Contrastive Learning and Generative Similarityby Raja Marjieh, Sreejan Kumar, Declan Campbell,…
MGDA Converges under Generalized Smoothness, Provablyby Qi Zhang, Peiyao Xiao, Shaofeng Zou, Kaiyi JiFirst submitted…
Deep Grokking: Would Deep Neural Networks Generalize Better?by Simin Fan, Razvan Pascanu, Martin JaggiFirst submitted…
Active Exploration via Autoregressive Generation of Missing Databy Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo,…
Clustering-Based Validation Splits for Model Selection under Domain Shiftby Andrea Napoli, Paul WhiteFirst submitted to…
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Databy Xuxing Chen, Abhishek Roy, Yifan…
The Data Minimization Principle in Machine Learningby Prakhar Ganesh, Cuong Tran, Reza Shokri, Ferdinando FiorettoFirst…
Online Nonparametric Supervised Learning for Massive Databy Mohamed Chaouch, Omama M. Al-HamedFirst submitted to arxiv…