SDCA without Duality, Regularization, and Individual Convexity
Autores:
Shai Shalev-Shwartz
Publicado en:
ICML, 2016
Editor:
ICML
Failures of Gradient-Based Deep Learning
Autores:
Shai Shalev-Shwartz, Ohad Shamir, Shaked Shammah
Publicado en:
ICML, 2017
Editor:
ICML
"Decoupling ""when to update"" from ""how to update"""
Autores:
Eran Malach, Shai Shalev-Shwartz
Publicado en:
NIPS, 2017
Editor:
Curran Associates, Inc.
Complexity theoretic limitations on learning DNF's
Autores:
Amit Daniely, Shai Shalev-Shwartz.
Publicado en:
COLT, 2016
Editor:
COLT
On Graduated Optimization for Stochastic Non-Convex Problems
Autores:
Elad Hazan, Kfir Y. Levy, Shai Shalev-Shwartz
Publicado en:
ICML, 2016
Editor:
ICML
Fast Rates for Empirical Risk Minimization of Strict Saddle Problems
Autores:
Alon Gonen, Shai Shalev-Shwartz
Publicado en:
COLT, 2017
Editor:
COLT
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Autores:
Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz
Publicado en:
International Conference on Learning Representations (ICLR), 2018
Editor:
ICLR
Solving Ridge Regression using Sketched Preconditioned SVRG
Autores:
Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz
Publicado en:
ICML, 2016
Editor:
ICML
On the Expressive Power of Overlapping Architectures of Deep Learning
Autores:
Or Sharir, Amnon Shashua
Publicado en:
ICLR, 2018
Editor:
ICLR
Sum-Product-Quotient Networks
Autores:
Or Sharir, Amnon Shashua
Publicado en:
AISTATS, 2018
Editor:
AISTATS
On the Long-Term Memory of Deep Recurrent Networks
Autores:
Yoav Levine, Or Sharir, Alon Ziv, Amnon Shashua
Publicado en:
ICLR, 2018
Editor:
ICLR workshop
