Global ETD Search

Meta-Learning & Compositional Generalization in Neural Networks

Schug, Simon; id_orcid0000-0002-5305-2547ETH Zurich2025

ethz Repository record for Meta-Learning & Compositional Generalization in Neural Networks (opens in a new tab)

Towards High-Dimensional Generalization in Neural Networks

Boopathy, AkhilanMassachusetts Institute of Technology2025

Neural networks excel in a wide range of applications due to their ability to generalize beyond training data. However, their performance degrades on high-dimensional tasks without large-scale data, a challenge known as the curse of dimensionality. This thesis addresses this limitation by pursuing …

mit Repository record for Towards High-Dimensional Generalization in Neural Networks (opens in a new tab)

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

Dziugaite, Gintare KarolinaUniversity of Cambridge2020

In this work, we construct generalization bounds to understand existing learning algorithms and propose new ones. Generalization bounds relate empirical performance to future expected performance. The tightness of these bounds vary widely, and depends on the complexity of the learning task and the …

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