paper-with-me

Papers

Convex Risk Minimization and Conditional Probability Estimation

2015-06-15 · Matus Telgarsky, Miroslav Dudík, Robert Schapire

This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any sequence of predictors minimizing convex risk over the source distribution will converge to this unique model when the class of predictors is linear (but potentially of infinite dimension). Secondly, we show the same result holds for \emph{empirical} risk minimization whenever this class of predictors is finite dimensional, where the essential technical contribution is a norm-free generalization bound.

📄 PDF Abstract BibTeX arXiv:1506.04513

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Combining T-learning and DR-learning: a framework for oracle-efficient estimation of causal contrasts

2024-02-03 · Lars van der Laan, Marco Carone, Alex Luedtke

We introduce efficient plug-in (EP) learning, a novel framework for the estimation of heterogeneous causal contrasts, such as the conditional average treatment effect and conditional relative risk. The EP-learning framew…

A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer

2017-09-09 · Tianbao Yang, Zhe Li, Lijun Zhang

In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with ex…

Stability and Sharper Risk Bounds with Convergence Rate $O(1/n^2)$

2024-10-13 · Bowei Zhu, Shaojie Li, Yong liu

The sharpest known high probability excess risk bounds are up to $O\left( 1/n \right)$ for empirical risk minimization and projected gradient descent via algorithmic stability (Klochkov \& Zhivotovskiy, 2021). In this pa…

On the Design of Loss Functions for Classification: theory, robustness to outliers, and SavageBoost

2008-12-01 · NeurIPS 2008 12 · Hamed Masnadi-Shirazi, Nuno Vasconcelos

The machine learning problem of classifier design is studied from the perspective of probability elicitation, in statistics. This shows that the standard approach of proceeding from the specification of a loss, to the mi…

General Classification

Statistical Analysis of Stationary Solutions of Coupled Nonconvex Nonsmooth Empirical Risk Minimization

2019-10-06 · Zhengling Qi, Ying Cui, Yufeng Liu, Jong-Shi Pang

This paper has two main goals: (a) establish several statistical properties---consistency, asymptotic distributions, and convergence rates---of stationary solutions and values of a class of coupled nonconvex and nonsmoot…

Retrieval