中文
相关论文

相关论文: Some Local Measures of Complexity of Convex Hulls …

200 篇论文

We introduce and study several measures of complexity of functions from the convex hull of a given base class. These complexity measures take into account the sparsity of the weights of a convex combination as well as certain clustering…

概率论 · 数学 2007-05-23 Vladimir Koltchinskii , Dmitry Panchenko

Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds that involve (various…

机器学习 · 统计学 2023-07-07 Sarah Sachs , Tim van Erven , Liam Hodgkinson , Rajiv Khanna , Umut Simsekli

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate the complexities with constraint on the expected norm to the corresponding ones with constraint on the empirical…

人工智能 · 计算机科学 2015-10-07 Yunwen Lei , Lixin Ding , Yingzhou Bi

Recently, metric learning and similarity learning have attracted a large amount of interest. Many models and optimisation algorithms have been proposed. However, there is relatively little work on the generalization analysis of such…

机器学习 · 计算机科学 2013-03-19 Qiong Cao , Zheng-Chu Guo , Yiming Ying

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense…

统计理论 · 数学 2007-06-13 Peter L. Bartlett , Olivier Bousquet , Shahar Mendelson

Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test error from the training error -- is a central theme of statistical learning theory. Among the…

机器学习 · 计算机科学 2026-05-26 Sho Sonoda , Kazumi Kasaura , Yuma Mizuno , Kei Tsukamoto , Naoto Onda

We study the fundamental problem of learning with respect to the squared loss in a convex class. The state-of-the-art sample complexity estimates in this setting rely on Rademacher complexities, which are generally difficult to control. We…

统计理论 · 数学 2025-02-24 Daniel Bartl , Shahar Mendelson

In this paper, we consider a new class of generalized Convex structure and we investigate their tropical limits. Some properties are pointing out such that translation homotheticity and others ones allowing to consider the case of discrete…

最优化与控制 · 数学 2024-08-16 Walter Briec , Stéphane Mussard , Paola Ravelojaona

This paper deals with the regularization of the sum of functions defined on a locally convex spaces through their closed-convex hulls in the bidual space. Different conditions guaranteeing that the closed-convex hull of the sum is the sum…

最优化与控制 · 数学 2024-10-11 Rafael Correa , Abderrahim Hantoute , Marco A. López

One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical…

统计理论 · 数学 2018-12-04 Khadija Musayeva , Fabien Lauer , Yann Guermeur

We study the problem of estimating the convex hull of the image $f(X)\subset\mathbb{R}^n$ of a compact set $X\subset\mathbb{R}^m$ with smooth boundary through a smooth function $f:\mathbb{R}^m\to\mathbb{R}^n$. Assuming that $f$ is a…

最优化与控制 · 数学 2024-03-11 Thomas Lew , Riccardo Bonalli , Lucas Janson , Marco Pavone

A method of proving local continuity of concave functions on convex set possessing the $\mu$-compactness property is presented. This method is based on a special approximation of these functions. The class of $\mu$-compact sets can be…

泛函分析 · 数学 2010-06-22 M. E. Shirokov

This paper studies the problem of learning weighted automata from a finite labeled training sample. We consider several general families of weighted automata defined in terms of three different measures: the norm of an automaton's weights,…

机器学习 · 计算机科学 2016-10-26 Borja Balle , Mehryar Mohri

We present a study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main result is a generalization…

机器学习 · 计算机科学 2020-10-06 Dylan J. Foster , Spencer Greenberg , Satyen Kale , Haipeng Luo , Mehryar Mohri , Karthik Sridharan

We extend the traditional worst-case, minimax analysis of stochastic convex optimization by introducing a localized form of minimax complexity for individual functions. Our main result gives function-specific lower and upper bounds on the…

机器学习 · 统计学 2016-05-27 Yuancheng Zhu , Sabyasachi Chatterjee , John Duchi , John Lafferty

A method is provided for computing an upper bound of the complexity of a module over a local ring, in terms of vanishing of certain cohomology modules. We then specialize to complete intersections, which are precisely the rings over which…

交换代数 · 数学 2007-06-26 Petter Andreas Bergh

We prove a new generalization bound that shows for any class of linear predictors in Gaussian space, the Rademacher complexity of the class and the training error under any continuous loss $\ell$ can control the test error under all Moreau…

机器学习 · 统计学 2022-10-24 Lijia Zhou , Frederic Koehler , Pragya Sur , Danica J. Sutherland , Nathan Srebro

As machine learning becomes more and more available to the general public, theoretical questions are turning into pressing practical issues. Possibly, one of the most relevant concerns is the assessment of our confidence in trusting machine…

机器学习 · 计算机科学 2020-06-30 Pietro Barbiero , Giovanni Squillero , Alberto Tonda

Statistical learning theory has largely focused on learning and generalization given independent and identically distributed (i.i.d.) samples. Motivated by applications involving time-series data, there has been a growing literature on…

机器学习 · 计算机科学 2019-06-24 Yuval Dagan , Constantinos Daskalakis , Nishanth Dikkala , Siddhartha Jayanti

Similarity learning has received a large amount of interest and is an important tool for many scientific and industrial applications. In this framework, we wish to infer the distance (similarity) between points with respect to an arbitrary…

机器学习 · 统计学 2016-11-30 Michael Rabadi
‹ 上一页 1 2 3 10 下一页 ›