The global convergence of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations
Institutions
Université Toulouse III - Paul Sabatier (FR)
Institut National des Sciences Appliquées de Toulouse (FR)
Laboratoire d'Informatique de Grenoble (FR)
Institut de Mathématiques de Toulouse (FR)
Publication Details
Journal
SPIRE - Sciences Po Institutional REpository
Published
2025-07-13
Primary Topic
Software-Defined Networks and 5G
Type
article
Field-Weighted Citation Impact
0.00
Funders
European Commission
Agence Nationale de la Recherche
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article
The global convergence of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations
Journal
SPIRE - Sciences Po Institutional REpository
Topics
Software-Defined Networks and 5G
article
The global convergence of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations
article en
Abstract
No abstract available for this paper.
Publication Tag
SPIRE - Sciences Po Institutional REpository
Institutions
Université Toulouse III - Paul Sabatier (FR), Institut National des Sciences Appliquées de Toulouse (FR), Laboratoire d'Informatique de Grenoble (FR), Institut de Mathématiques de Toulouse (FR)
Funders
European Commission, Agence Nationale de la Recherche
Ask Laika to Summarize, Analyze, and Connect papers live on the map.
Summarize Papers & Methodologies
Extract key findings, datasets, and comparative methods across publications.
Benchmark Rankings & Visual Analytics
Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.
Connect Distant Disciplines
Bridge topological clusters on the map to find hidden collaborative intersections.
The global convergence of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations · SPIRE - Sciences Po Institutional REpository (2025) | TGRS Research Map | TGRS