ResearchTrend.AI
Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond

Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond

Nina Vesseron
I. Redko
Charlotte Laclau
ArXiv (abs)PDFHTML

Papers citing "Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond"

6 / 6 papers shown
Title
A Mean Field View of the Landscape of Two-Layers Neural Networks
A Mean Field View of the Landscape of Two-Layers Neural Networks
Song Mei
Andrea Montanari
Phan-Minh Nguyen
MLT
109
863
0
18 Apr 2018
Identity Matters in Deep Learning
Identity Matters in Deep Learning
Moritz Hardt
Tengyu Ma
OOD
99
399
0
14 Nov 2016
Topology and Geometry of Half-Rectified Network Optimization
Topology and Geometry of Half-Rectified Network Optimization
C. Freeman
Joan Bruna
235
235
0
04 Nov 2016
Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition
Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition
Rong Ge
Furong Huang
Chi Jin
Yang Yuan
146
1,059
0
06 Mar 2015
Qualitatively characterizing neural network optimization problems
Qualitatively characterizing neural network optimization problems
Ian Goodfellow
Oriol Vinyals
Andrew M. Saxe
ODL
118
524
0
19 Dec 2014
Learning to Cooperate via Policy Search
Learning to Cooperate via Policy Search
L. Peshkin
Kee-Eung Kim
Nicolas Meuleau
L. Kaelbling
OffRL
89
306
0
07 Aug 2014