"flat minima" · 3 results · Global ETD Search

Revisiting Generalization for Deep Learning: PAC-Bayes, Flat Minima, and Generative Models

Dziugaite, Gintare KarolinaUniversity of Cambridge2020

… learning. By formalizing the notion of flat minima using PAC-Bayes generalization bounds, we obtain nonvacuous generalization bounds for stochastic classifiers based on SGD solutions. Despite strong empirical performance in many settings, SGD rapidly overfits in others. By combining …

cambridge Repository record for Revisiting Generalization for Deep Learning: PAC-Bayes, Flat Minima, and Generative Models (opens in a new tab)

Making Sense of Training Large AI Models

Ahn, KwangjunMassachusetts Institute of Technology2024

… We then discuss its connection to popular flat minima optimization algorithms, and initiate a formal study of them by defining a formal notion of flat minima, and analyzing the complexities of finding them.

mit Repository record for Making Sense of Training Large AI Models (opens in a new tab)

Advancing Generalization in Heterogeneous Federated Learning for Real-world Vision Applications

CALDAROLA, DEBORAPolitecnico di Torino2024

L'abstract è presente nell'allegato / the abstract is in the attachment

poli-torino Repository record for Advancing Generalization in Heterogeneous Federated Learning for Real-world Vision Applications (opens in a new tab)

Global ETD Search

Results

Revisiting Generalization for Deep Learning: PAC-Bayes, Flat Minima, and Generative Models

Making Sense of Training Large AI Models

Advancing Generalization in Heterogeneous Federated Learning for Real-world Vision Applications