On the Implicit Bias of Gradient Descent for Temporal Extrapolation

v1v2 (latest)

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

International Conference on Artificial Intelligence and Statistics (AISTATS), 2022

9 February 2022

Edo Cohen-Karlik

Avichai Ben David

ArXiv (abs)PDF HTML

Papers citing "On the Implicit Bias of Gradient Descent for Temporal Extrapolation"

3 / 3 papers shown

Title
A Minimum Description Length Approach to Regularization in Neural Networks Matan Abudy Orr Well Emmanuel Chemla Roni Katzir Nur Lan 259 2 0 19 May 2025
Deep Neural Networks Tend To Extrapolate PredictablyInternational Conference on Learning Representations (ICLR), 2023 Katie Kang Amrith Rajagopal Setlur Claire Tomlin Sergey Levine 193 0 0 02 Oct 2023
Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural NetsInternational Conference on Learning Representations (ICLR), 2022 Edo Cohen-Karlik Itamar Menuhin-Gruman Raja Giryes Nadav Cohen Amir Globerson 355 7 0 25 Oct 2022