Step Size Matters in Deep Learning

22 May 2018

Papers citing "Step Size Matters in Deep Learning"

8 / 8 papers shown

Title
GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms Chinedu Eleh Masuzyo Mwanza Ekene S. Aguegboh Hans-Werner van Wyk 21 0 0 25 May 2024
Why is SAM Robust to Label Noise? Christina Baek Zico Kolter Aditi Raghunathan NoLa AAML 43 9 0 06 May 2024
Faster Convergence for Transformer Fine-tuning with Line Search Methods Philip Kenneweg Leonardo Galli Tristan Kenneweg Barbara Hammer ODL 46 2 0 27 Mar 2024
On the Implicit Bias in Deep-Learning Algorithms Gal Vardi FedML AI4CE 34 72 0 26 Aug 2022
Augment your batch: better training with larger batches Elad Hoffer Tal Ben-Nun Itay Hubara Niv Giladi Torsten Hoefler Daniel Soudry ODL 30 72 0 27 Jan 2019
Cross-Entropy Loss and Low-Rank Features Have Responsibility for Adversarial Examples Kamil Nar Orhan Ocal S. Shankar Sastry Kannan Ramchandran AAML 27 54 0 24 Jan 2019
Representing smooth functions as compositions of near-identity functions with implications for deep network optimization Peter L. Bartlett S. Evans Philip M. Long 76 31 0 13 Apr 2018
L4: Practical loss-based stepsize adaptation for deep learning Michal Rolínek Georg Martius ODL 44 63 0 14 Feb 2018