Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks

to related objects

Location: Deutsche Nationalbibliothek Frankfurt am Main

Extent: 1 Online-Ressource.

Language: Englisch

Bibliographic citation: Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks ; day:10 ; month:9 ; year:2024 ; pages:1-32
Journal of optimization theory and applications ; (10.9.2024), 1-32

Creator: Cheridito, Patrick
Jentzen, Arnulf
Rossmannek, Florian

Contributor: SpringerLink (Online service)

DOI: 10.1007/s10957-024-02513-3

URN: urn:nbn:de:101:1-2411242108572.454330767940

Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.

Last update: 15.08.2025, 7:34 AM CEST

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.

Show original at data provider

Associated

Cheridito, Patrick
Jentzen, Arnulf
Rossmannek, Florian
SpringerLink (Online service)

Other Objects (12)

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Bilderbuch | Sachbücher und Sachbilderbücher für Kinder und Jugendliche: Geschichte, Politik

Legendary escapes

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Bilderbuch | Sachbücher und Sachbilderbücher für Kinder und Jugendliche: Geschichte, Politik

Legendary escapes

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Bilderbuch | Sachbücher und Sachbilderbücher für Kinder und Jugendliche: Geschichte, Politik

Legendary escapes

Cultural heritage institutions wishing to register will find more information here.

Fields marked * need to be filled in.

Username*

Please enter your username

Email*

Please enter your email address

Please do not fill this field

First name

Last name

Password*

Please enter your password

Confirm password*

Please enter the same password

I have read the terms of use and the privacy policy for the collection of personal data and accept them. *

This field is required.

I would like to subscribe to the newsletter of the Deutsche Digitale Bibliothek. See newsletter subscription info.

Account created

Your "My DDB" account has been successfully created. Before you can log in to your account, you must click the confirmation link in the message we just sent to the email address you provided.

Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks

Object Details

References and Relationships

Contributors, Places and Time

Further information

Data provider

Associated

Other Objects (12)

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Legendary escapes

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Legendary escapes

Sequential escapes: onset of slow domino regime via a saddle connection

Gradient descent akin method

Adaptive hierarchical hyper-gradient descent

On Cyclic Gradient Descent Reprojection

Gradient descent on parametric Markov Chains

Stochastic gradient descent for wind farm optimization

cPro: Circular Projections Using Gradient Descent

Adaptive Step Sizes for Stochastic Gradient Descent

Bolstering stochastic gradient descent with model building

Scalable stochastic gradient descent with improved confidence

Local Convergence of Adaptive Gradient Descent Optimizers

Legendary escapes

Related objects

Reset password