Momentum-SAM: Sharpness Aware Minimization without Computational Overheadby Marlon Becker, Frederick Altrock, Benjamin RisseFirst submitted to…
Asynchronous Local-SGD Training for Language Modelingby Bo Liu, Rachita Chhaparia, Arthur Douillard, Satyen Kale, Andrei…
An ADRC-Incorporated Stochastic Gradient Descent Algorithm for Latent Factor Analysisby Jinli Li, Ye YuanFirst submitted…
Deep Learning Based Cyberbullying Detection in Bangla Languageby Sristy Shidul Nath, Razuan Karim, Mahdi H.…
Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systemsby Ori Shem-Ur, Yaron…
Convex SGD: Generalization Without Early Stoppingby Julien Hendrickx, Alex OlshevskyFirst submitted to arxiv on: 8…
AA-DLADMM: An Accelerated ADMM-based Framework for Training Deep Neural Networksby Zeinab Ebrahimi, Gustavo Batista, Mohammad…
Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reductionby Jie Feng, Ke Wei,…
Stochastic Gradient Descent for Nonparametric Regressionby Xin Chen, Jason M. KlusowskiFirst submitted to arxiv on:…
Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learnersby Rachel Redberg,…