paper-with-me

Papers

Non-Asymptotic PAC-Bayes Bounds on Generalisation Error

2021-01-01 · Arijit Das

Constructing non-vacuous PAC-Bayes bounds on generalization errors for un- bounded risk functionals, especially in the non-asymptotic regime, is an active area of research. However, current state of the art results are applicable only in some very specialized cases. In this work, we give an integrability condition which exactly characterizes when any risk functional, for a given data set and model space, admits such bounds using the Levy-Khintchine theorem. Further, we de- rive a Bahadur-Rao type exact asymptotic bound, which is much sharper than a traditional Chernoff type inequality, especially in the under-sampled regime. These bounds give us the flexibility to construct data or model-dependent consistency promoting updates to a data-free prior, which provably improves the generalization performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Non-Vacuous Generalisation Bounds for Shallow Neural Networks

2022-02-03 · Felix Biggs, Benjamin Guedj

We focus on a specific class of shallow neural networks with a single hidden layer, namely those with $L_2$-normalised data and either a sigmoid-shaped Gaussian error function ("erf") activation or a Gaussian Error Linea…

Chained Generalisation Bounds

2022-03-02 · Eugenio Clerico, Amitis Shidani, George Deligiannidis, Arnaud Doucet

This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a dua…

How Tight Can PAC-Bayes be in the Small Data Regime?

2021-06-07 · NeurIPS 2021 12 · Andrew Y. K. Foong, Wessel P. Bruinsma, David R. Burt, Richard E. Turner

In this paper, we investigate the question: Given a small number of datapoints, for example N = 30, how tight can PAC-Bayes and test set bounds be made? For such small datasets, test set bounds adversely affect generalis…

How Tight Can PAC-Bayes be in the Small Data Regime?

2021-12-01 · NeurIPS 2021 12 · Andrew Foong, Wessel Bruinsma, David Burt, Richard Turner

In this paper, we investigate the question: _Given a small number of datapoints, for example $N = 30$, how tight can PAC-Bayes and test set bounds be made?_ For such small datasets, test set bounds adversely affect gener…

Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisation

2023-04-14 · Maxime Haddouche, Benjamin Guedj

PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the e…