中文
相关论文

相关论文: Trading off Consistency and Dimensionality of Conv…

200 篇论文

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and…

机器学习 · 计算机科学 2015-08-25 Harish G. Ramaswamy , Shivani Agarwal

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many…

机器学习 · 计算机科学 2022-06-30 Jessie Finocchiaro , Rafael M. Frongillo , Bo Waggoner

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many…

机器学习 · 计算机科学 2022-01-12 Jessie Finocchiaro , Rafael Frongillo , Bo Waggoner

Given a prediction task, understanding when one can and cannot design a consistent convex surrogate loss, particularly a low-dimensional one, is an important and active area of machine learning research. The prediction task may be given as…

机器学习 · 计算机科学 2021-02-17 Jessie Finocchiaro , Rafael Frongillo , Bo Waggoner

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via…

机器学习 · 计算机科学 2018-01-30 Anton Osokin , Francis Bach , Simon Lacoste-Julien

We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analysis of consistency properties to the case of inconsistent…

机器学习 · 计算机科学 2019-01-10 Kirill Struminsky , Simon Lacoste-Julien , Anton Osokin

In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a proxy for minimizing the $0/1$ loss in the presence of an…

机器学习 · 计算机科学 2022-05-23 Laurent Meunier , Raphaël Ettedgui , Rafael Pinot , Yann Chevaleyre , Jamal Atif

We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labels. Very recently, this approach was put into question by a…

机器学习 · 计算机科学 2012-07-03 Krzysztof Dembczynski , Wojciech Kotlowski , Eyke Huellermeier

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case…

Commonly used classification algorithms in machine learning, such as support vector machines, minimize a convex surrogate loss on training examples. In practice, these algorithms are surprisingly robust to errors in the training data. In…

机器学习 · 计算机科学 2020-12-03 Kunal Talwar

Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns. This problem is often formulated via a minimax objective, where the target loss is the worst-case value of the 0-1…

机器学习 · 统计学 2021-05-14 Han Bao , Clayton Scott , Masashi Sugiyama

We consider the problem of $n$-class classification ($n\geq 2$), where the classifier can choose to abstain from making predictions at a given cost, say, a factor $\alpha$ of the cost of misclassification. Designing consistent algorithms…

机器学习 · 计算机科学 2015-05-18 Harish G. Ramaswamy , Ambuj Tewari , Shivani Agarwal

This paper presents a novel learning-based approach to construct a surrogate problem that approximates a given parametric nonconvex optimization problem. The surrogate function is designed to be the minimum of a finite set of functions,…

最优化与控制 · 数学 2026-04-08 Renzi Wang , Panagiotis Patrinos , Alberto Bemporad

Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar…

机器学习 · 计算机科学 2025-05-27 Ryan D'Orazio , Danilo Vucetic , Zichu Liu , Junhyung Lyle Kim , Ioannis Mitliagkas , Gauthier Gidel

Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the adversarial loss with most hypothesis sets is NP-hard. But…

机器学习 · 计算机科学 2021-05-05 Pranjal Awasthi , Natalie Frank , Anqi Mao , Mehryar Mohri , Yutao Zhong

The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while piecewise-linear losses (like Hinge)…

机器学习 · 计算机科学 2026-05-01 Mehryar Mohri , Yutao Zhong

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed…

机器学习 · 计算机科学 2014-02-11 Mehrdad Mahdavi , Lijun Zhang , Rong Jin

Solving optimization problems with unknown parameters often requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values. Recent work has shown that including the…

机器学习 · 计算机科学 2020-10-23 Kai Wang , Bryan Wilder , Andrew Perrault , Milind Tambe

The statistical consistency of surrogate losses for discrete prediction tasks is often checked via the condition of calibration. However, directly verifying calibration can be arduous. Recent work shows that for polyhedral surrogates, a…

机器学习 · 计算机科学 2025-05-21 Drona Khurana , Anish Thilagar , Dhamma Kimpara , Rafael Frongillo

We present a detailed study of surrogate losses and algorithms for multi-label learning, supported by $H$-consistency bounds. We first show that, for the simplest form of multi-label loss (the popular Hamming loss), the well-known…

机器学习 · 计算机科学 2024-07-19 Anqi Mao , Mehryar Mohri , Yutao Zhong
‹ 上一页 1 2 3 10 下一页 ›