paper-with-me

홈 › Papers

Empirical risk minimization algorithm for multiclass classification of S.D.E. paths

2025-03-18 · Christophe Denis, Eddy Ella Mintsa

We address the multiclass classification problem for stochastic diffusion paths, assuming that the classes are distinguished by their drift functions, while the diffusion coefficient remains common across all classes. In this setting, we propose a classification algorithm that relies on the minimization of the L 2 risk. We establish rates of convergence for the resulting predictor. Notably, we introduce a margin assumption under which we show that our procedure can achieve fast rates of convergence. Finally, a simulation study highlights the numerical performance of our classification algorithm.

📄 PDF Abstract BibTeX arXiv:2503.14045

Code (0)

등록된 구현이 없습니다.

Tasks

Classification

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Statistical learning by sparse deep neural networks

2023-11-15 · Felix Abramovich

We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization. We derive a general bound for its excess risk in regression and classification (including multiclass), and prove t…

regression

Adversarial Multiclass Classification: A Risk Minimization Perspective

2016-12-01 · NeurIPS 2016 12 · Rizal Fathony, Anqi Liu, Kaiser Asif, Brian Ziebart

Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses. In contrast with empirical risk minimization (ERM) methods, which use convex surrogate losses …

ClassificationGeneral Classification

FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression

2024-09-11 · NeurIPS 2023 11 · Youguang Chen, George Biros

We investigate theory and algorithms for pool-based active learning for multiclass classification using multinomial logistic regression. Using finite sample analysis, we prove that the Fisher Information Ratio (FIR) lowe…

Active Learningregression

Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation

2021-06-21 · NeurIPS 2021 12 · Ke Wang, Vidya Muthukumar, Christos Thrampoulidis

The literature on "benign overfitting" in overparameterized models has been mostly restricted to regression or binary classification; however, modern machine learning operates in the multiclass setting. Motivated by this…

AllBinary ClassificationClassification

Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement

2026-01-31 · Bryan Zhu, Ziang Chen arxiv

Empirical risk minimization (ERM) can be computationally expensive, with standard solvers scaling poorly even in the convex setting. We propose a novel lossless compression framework for convex ERM based on color refinem…