paper-with-me

홈 › Papers

Generalization bounds for deep learning

2020-12-07 · Guillermo Valle-Pérez, Ard A. Louis

Generalization in deep learning has been the topic of much recent theoretical and empirical research. Here we introduce desiderata for techniques that predict generalization errors for deep learning models in supervised learning. Such predictions should 1) scale correctly with data complexity; 2) scale correctly with training set size; 3) capture differences between architectures; 4) capture differences between optimization algorithms; 5) be quantitatively not too far from the true error (in particular, be non-vacuous); 6) be efficiently computable; and 7) be rigorous. We focus on generalization error upper bounds, and introduce a categorisation of bounds depending on assumptions on the algorithm and data. We review a wide range of existing approaches, from classical VC dimension to recent PAC-Bayesian bounds, commenting on how well they perform against the desiderata. We next use a function-based picture to derive a marginal-likelihood PAC-Bayesian bound. This bound is, by one definition, optimal up to a multiplicative constant in the asymptotic limit of large training sets, as long as the learning curve follows a power law, which is typically found in practice for deep learning problems. Extensive empirical analysis demonstrates that our marginal-likelihood PAC-Bayes bound fulfills desiderata 1-3 and 5. The results for 6 and 7 are promising, but not yet fully conclusive, while only desideratum 4 is currently beyond the scope of our bound. Finally, we comment on why this function-based bound performs significantly better than current parameter-based PAC-Bayes bounds.

📄 PDF Abstract BibTeX arXiv:2012.04115

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneralization Bounds

Similar Papers 제목 키워드 기반

Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms

2021-02-03 · Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues

Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical…

BIG-bench Machine Learning

Which Algorithms Have Tight Generalization Bounds?

2024-10-02 · Michael Gastpar, Ido Nachum, Jonathan Shafer, Thomas Weinberger

We study which machine learning algorithms have tight generalization bounds. First, we present conditions that preclude the existence of tight generalization bounds. Specifically, we show that algorithms that have certai…

Generalization Bounds

An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics

2024-03-29 · Wenliang Liu, Guanding Yu, Lele Wang, Renjie Liao

We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that establishes information-theoretic generalization bounds. Our framework interpolates freely between Integral P…

Generalization BoundsOut-of-Distribution Generalization

Formal limitations of sample-wise information-theoretic generalization bounds

2022-05-13 · Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan

Some of the tightest information-theoretic generalization bounds depend on the average information between the learned hypothesis and a single training example. However, these sample-wise bounds were derived only for exp…

Generalization Bounds

Fantastic Generalization Measures are Nowhere to be Found

2023-09-24 · Michael Gastpar, Ido Nachum, Jonathan Shafer, Thomas Weinberger

We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous g…

Generalization Bounds