all AI news
The Implicit Regularization of Momentum Gradient Descent with Early Stopping. (arXiv:2201.05405v1 [cs.LG])
Jan. 17, 2022, 2:10 a.m. | Li Wang (1), Yingcong Zhou (2), Zhiguo Fu (1) ((1) Northeast Normal University, (2) Beihua University)
cs.LG updates on arXiv.org arxiv.org
The study on the implicit regularization induced by gradient-based
optimization is a longstanding pursuit. In the present paper, we characterize
the implicit regularization of momentum gradient descent (MGD) with early
stopping by comparing with the explicit $\ell_2$-regularization (ridge). In
details, we study MGD in the continuous-time view, so-called momentum gradient
flow (MGF), and show that its tendency is closer to ridge than the gradient
descent (GD) [Ali et al., 2019] for least squares regression. Moreover, we
prove that, under the …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Analyst
@ Rappi | COL-Bogotá
Applied Scientist II
@ Microsoft | Redmond, Washington, United States