Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Savarese, Pedro H. P."'
Autor:
Nacson, Mor Shpigel, Lee, Jason D., Gunasekar, Suriya, Savarese, Pedro H. P., Srebro, Nathan, Soudry, Daniel
We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the conditions on the t
Externí odkaz:
http://arxiv.org/abs/1803.01905
From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets
Publikováno v:
Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, New Orleans, Louisiana, USA, February 2-7, 2018
We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC) estimators of Restricted Boltzmann Machines (RBMs). We denote our approach Markov Chain Las Vegas (MCLV). MCLV gives statistical guarantees in exchange for random running times.
Externí odkaz:
http://arxiv.org/abs/1711.08442
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only r
Externí odkaz:
http://arxiv.org/abs/1704.03165
We propose a new layer design by adding a linear gating mechanism to shortcut connections. By using a scalar parameter to control each gate, we provide a way to learn identity mappings by optimizing only one parameter. We build upon the motivation be
Externí odkaz:
http://arxiv.org/abs/1611.01260