paper-with-me

홈 › Papers

PAC-Bayes unleashed: generalisation bounds with unbounded losses

2020-06-12 · Maxime Haddouche, Benjamin Guedj, Omar Rivasplata, John Shawe-Taylor

We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions. This extends the relevance and applicability of the PAC-Bayes learning framework, where most of the existing literature focuses on supervised learning problems with a bounded loss function (typically assumed to take values in the interval [0;1]). In order to relax this assumption, we propose a new notion called HYPE (standing for \emph{HYPothesis-dependent rangE}), which effectively allows the range of the loss to depend on each predictor. Based on this new notion we derive a novel PAC-Bayesian generalisation bound for unbounded loss functions, and we instantiate it on a linear regression problem. To make our theory usable by the largest audience possible, we include discussions on actual computation, practicality and limitations of our assumptions.

📄 PDF Abstract BibTeX arXiv:2006.07279

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales

2022-10-03 · Maxime Haddouche, Benjamin Guedj

While PAC-Bayes is now an established learning framework for light-tailed losses (\emph{e.g.}, subgaussian or subexponential), its extension to the case of heavy-tailed losses remains largely uncharted and has attracted …

A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning

2026-05-25 · Thien V. Nguyen, Amaury Habrard, Benjamin Guedj arxiv

Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically in the form of partial differential equations (PDE), into data-driven models. Despite strong empirical performance, its statistical gen…

Learning via Wasserstein-Based High Probability Generalisation Bounds

2023-06-07 · NeurIPS 2023 11

Minimising upper bounds on the population risk or the generalisation gap has been widely used in structural risk minimisation (SRM) -- this is in particular at the core of PAC-Bayesian learning. Despite its successes and…

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

2024-09-26 · Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence. Previ…

Generalization Boundsvalid

PAC-Bayes-Chernoff bounds for unbounded losses

2024-01-02 · Ioar Casado, Luis A. Ortega, Aritz Pérez, Andrés R. Masegosa

We introduce a new PAC-Bayes oracle bound for unbounded losses that extends Cram\'er-Chernoff bounds to the PAC-Bayesian setting. The proof technique relies on controlling the tails of certain random variables involving …