Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Seroussi, Inbar"'
Autor:
Collins-Woodfin, Elizabeth, Seroussi, Inbar, Malaxechebarría, Begoña García, Mackenzie, Andrew W., Paquette, Elliot, Paquette, Courtney
We develop a framework for analyzing the training and learning rate dynamics on a large class of high-dimensional optimization problems, which we call the high line, trained using one-pass stochastic gradient descent (SGD) with adaptive learning rate
Externí odkaz:
http://arxiv.org/abs/2405.19585
A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a sudden increase
Externí odkaz:
http://arxiv.org/abs/2310.03789
We analyze the dynamics of streaming stochastic gradient descent (SGD) in the high-dimensional limit when applied to generalized linear models and multi-index models (e.g. logistic regression, phase retrieval) with general data-covariance. In particu
Externí odkaz:
http://arxiv.org/abs/2308.08977
State-of-the-art neural networks require extreme computational power to train. It is therefore natural to wonder whether they are optimally trained. Here we apply a recent advancement in stochastic thermodynamics which allows bounding the speed at wh
Externí odkaz:
http://arxiv.org/abs/2307.14653
Physically informed neural networks (PINNs) are a promising emerging method for solving differential equations. As in many other deep learning approaches, the choice of PINN design and training protocol requires careful craftsmanship. Here, we sugges
Externí odkaz:
http://arxiv.org/abs/2307.06362
Deep neural networks (DNNs) are powerful tools for compressing and distilling information. Their scale and complexity, often involving billions of inter-dependent parameters, render direct microscopic analysis difficult. Under such circumstances, a c
Externí odkaz:
http://arxiv.org/abs/2112.15383
Autor:
Seroussi, Inbar, Zeitouni, Ofer
We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that unbiased est
Externí odkaz:
http://arxiv.org/abs/2103.14723
We study the directed polymer model for general graphs (beyond $\mathbb Z^d$) and random walks. We provide sufficient conditions for the existence or non-existence of a weak disorder phase, of an $L^2$ region, and of very strong disorder, in terms of
Externí odkaz:
http://arxiv.org/abs/2010.09503
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Seroussi, Inbar, Sochen, Nir
Publikováno v:
Physica A: Statistical Mechanics and its Applications (2020): 124636
Dynamics among central sources (hubs) providing a resource and large number of components enjoying and contributing to this resource describes many real life situations. Modeling, controlling, and balancing this dynamics is a general problem that ari
Externí odkaz:
http://arxiv.org/abs/1908.00068