Self‐Certifying Classification by Linearized Deep Assignment
Abstract: We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC‐Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with random initial conditions. Building on the recent PAC‐Bayes literature and data‐dependent priors, this approach enables (i) to use risk bounds as training objectives for learning posterior distributions on the hypothesis space and (ii) to compute tight out‐of‐sample risk certificates of randomized classifiers more efficiently than related work. Comparison with empirical test set errors illustrates the performance and practicality of this self‐certifying classification method.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Self‐Certifying Classification by Linearized Deep Assignment ; volume:23 ; number:1 ; year:2023 ; extent:6
Proceedings in applied mathematics and mechanics ; 23, Heft 1 (2023) (gesamt 6)
- Urheber
- DOI
-
10.1002/pamm.202200169
- URN
-
urn:nbn:de:101:1-2023060115141258953453
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 10:52 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Boll, Bastian
- Zeilmann, Alexander
- Petra, Stefania
- Schnörr, Christoph
Ähnliche Objekte (12)
Self‐certifying classification by linearized deep assignment
Learning Linearized Assignment Flows for Image Labeling
Robust mixing in self-consistent linearized augmented planewave calculations
Holographic isotropization linearized
Task assignment by self-organizing maps
New GOLD classification: longitudinal data on group assignment
A linearized free-surface RANS method for self-propulsion and maneuvering
Erratum: New GOLD classification: longitudinal data on group assignment
The dynamics of linearized polynomials
Jet wake from linearized hydrodynamics
A self-interpretable module for deep image classification on small data
Assignment
Self‐certifying classification by linearized deep assignment
Learning Linearized Assignment Flows for Image Labeling
Robust mixing in self-consistent linearized augmented planewave calculations
Holographic isotropization linearized
Task assignment by self-organizing maps
New GOLD classification: longitudinal data on group assignment
A linearized free-surface RANS method for self-propulsion and maneuvering
Erratum: New GOLD classification: longitudinal data on group assignment
The dynamics of linearized polynomials
Jet wake from linearized hydrodynamics
A self-interpretable module for deep image classification on small data
Assignment
Self‐certifying classification by linearized deep assignment
Learning Linearized Assignment Flows for Image Labeling
Robust mixing in self-consistent linearized augmented planewave calculations
Holographic isotropization linearized
Task assignment by self-organizing maps
New GOLD classification: longitudinal data on group assignment
A linearized free-surface RANS method for self-propulsion and maneuvering
Erratum: New GOLD classification: longitudinal data on group assignment
The dynamics of linearized polynomials
Jet wake from linearized hydrodynamics
A self-interpretable module for deep image classification on small data