A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequalityby Kushal Chakrabarti, Mayank…
Why Do You Grok? A Theoretical Analysis of Grokking Modular Additionby Mohamad Amin Mohamadi, Zhiyuan…
Quantum Maximum Entropy Inference and Hamiltonian Learningby Minbo Gao, Zhengfeng Ji, Fuchao WeiFirst submitted to…
Preconditioned Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regressionby Yingzhen YangFirst…
Learning by the F-adjointby Ahmed BoughammouraFirst submitted to arxiv on: 8 Jul 2024CategoriesMain: Machine Learning…
Correlations Are Ruining Your Gradient Descentby Nasir AhmadFirst submitted to arxiv on: 15 Jul 2024CategoriesMain:…
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyondby Yingcong Li, Ankit Singh Rawat,…
Differentially Private Neural Network Training under Hidden State Assumptionby Ding Chen, Chen LiuFirst submitted to…
Faster Machine Unlearning via Natural Gradient Descentby Omri Lev, Ashia WilsonFirst submitted to arxiv on:…
CONGO: Compressive Online Gradient Optimizationby Jeremy Carleton, Prathik Vijaykumar, Divyanshu Saxena, Dheeraj Narasimha, Srinivas Shakkottai,…