paper-with-me

Papers

Misclassification excess risk bounds for PAC-Bayesian classification via convexified loss

2024-08-16 · The Tien Mai

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen loss function. In classification tasks, due to the non-convex nature of the 0-1 loss, a convex surrogate loss is often used, and thus current PAC-Bayesian bounds are primarily specified for this convex surrogate. This work shifts its focus to providing misclassification excess risk bounds for PAC-Bayesian classification when using a convex surrogate loss. Our key ingredient here is to leverage PAC-Bayesian relative bounds in expectation rather than relying on PAC-Bayesian bounds in probability. We demonstrate our approach in several important applications.

📄 PDF Abstract BibTeX arXiv:2408.08675

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

High Dimensional Classification through $\ell_0$-Penalized Empirical Risk Minimization

2018-11-23 · Le-Yu Chen, Sokbae Lee

We consider a high dimensional binary classification problem and construct a classification procedure by minimizing the empirical misclassification risk with a penalty on the number of selected features. We derive non-as…

Binary ClassificationClassificationGeneral ClassificationVocal Bursts Intensity Prediction

Misclassification excess risk bounds for 1-bit matrix completion

2023-12-20 · The Tien Mai

This study investigates the misclassification excess risk bound in the context of 1-bit matrix completion, a significant problem in machine learning involving the recovery of an unknown matrix from a limited subset of it…

Matrix Completion

PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification

2012-02-28 · Emilie Morvant, Sokol Koço, Liva Ralaivola

In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classif…

General ClassificationMulti-class Classification

Information-Theoretic Analysis of Minimax Excess Risk

2022-02-15 · Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei

Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theo…

Learning Theory

High-dimensional classification by sparse logistic regression

2017-06-26 · Felix Abramovich, Vadim Grinshtein

We consider high-dimensional binary classification by sparse logistic regression. We propose a model/feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and deriv…

Binary ClassificationClassificationfeature selectionGeneral Classification+3