English
Related papers

Related papers: Stable Sample Compression Schemes: New Application…

200 papers

The linear Support Vector Machine (SVM) is a classic classification technique in machine learning. Motivated by applications in modern high dimensional statistics, we consider penalized SVM problems involving the minimization of a…

Machine Learning · Statistics 2021-08-31 Antoine Dedieu , Rahul Mazumder , Haoyue Wang

The support vector machine (SVM) algorithm is well known to the computer learning community for its very good practical results. The goal of the present paper is to study this algorithm from a statistical perspective, using tools of…

Statistics Theory · Mathematics 2008-12-18 Gilles Blanchard , Olivier Bousquet , Pascal Massart

In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of its margin (i.e., the expected margin and the voters'…

Machine Learning · Statistics 2021-09-01 Paul Viallard , Pascal Germain , Amaury Habrard , Emilie Morvant

This paper deals with the scenario approach to robust optimization. This relies on a random sampling of the possibly infinite number of constraints induced by uncertainties in the parameters of an optimization problem. Solving the resulting…

Optimization and Control · Mathematics 2023-03-08 Fabien Lauer

Sample compression schemes were defined by Littlestone and Warmuth (1986) as an abstraction of the structure underlying many learning algorithms. Roughly speaking, a sample compression scheme of size $k$ means that given an arbitrary list…

Machine Learning · Computer Science 2015-04-15 Shay Moran , Amir Yehudayoff

We study randomized algorithms for constrained optimization, in abstract frameworks that include, in strictly increasing generality: convex programming; LP-type problems; violator spaces; and a setting we introduce, consistent spaces. Such…

Computational Geometry · Computer Science 2019-06-04 Kenneth L. Clarkson , Bernd Gärtner , Johannes Lengler , May Szedlak

We develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive application of linear…

Optimization and Control · Mathematics 2015-03-25 Yossi Arjevani , Shai Shalev-Shwartz , Ohad Shamir

The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo…

Machine Learning · Statistics 2020-10-27 Hao Wu , Jonas Köhler , Frank Noé

Motion planning is a central challenge in robotics, with learning-based approaches gaining significant attention in recent years. Our work focuses on a specific aspect of these approaches: using machine-learning techniques, particularly…

Robotics · Computer Science 2025-02-07 Sapir Tubul , Aviv Tamar , Kiril Solovey , Oren Salzman

In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is that we propose to use the confusion matrix of a classifier as…

Machine Learning · Computer Science 2012-05-25 Pierre Machart , Liva Ralaivola

Support vector machine (SVM) is one of the most popular classification algorithms in the machine learning literature. We demonstrate that SVM can be used to balance covariates and estimate average causal effects under the unconfoundedness…

Methodology · Statistics 2021-07-02 Alexander Tarr , Kosuke Imai

Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In this paper we provide a PAC bound that holds for these kind…

Machine Learning · Computer Science 2025-05-27 Dániel Rácz , Mihály Petreczky , Bálint Daróczy

We present the first sample compression algorithm for nearest neighbors with non-trivial performance guarantees. We complement these guarantees by demonstrating almost matching hardness lower bounds, which show that our bound is nearly…

Machine Learning · Computer Science 2018-03-28 Lee-Ad Gottlieb , Aryeh Kontorovich , Pinhas Nisnevitch

Objective: Classifier transfers usually come with dataset shifts. To overcome them, online strategies have to be applied. For practical applications, limitations in the computational resources for the adaptation of batch learning…

Machine Learning · Computer Science 2022-08-11 Mario Michael Krell , Nils Wilshusen , Anett Seeland , Su Kyoung Kim

Weighted SVM (or fuzzy SVM) is the most widely used SVM variant owning its effectiveness to the use of instance weights. Proper selection of the instance weights can lead to increased generalization performance. In this work, we extend the…

Machine Learning · Computer Science 2018-09-18 Ioannis Sarafis , Christos Diou , Anastasios Delopoulos

We study stochastic nonconvex optimization under heavy-tailed noise. In this setting, the stochastic gradients only have bounded $p$-th central moment ($p$-BCM) for some $p \in (1,2]$. Building on the foundational work of Arjevani et al.…

Optimization and Control · Mathematics 2026-04-01 Adrien Fradin , Abdurakhmon Sadiev , Laurent Condat , Peter Richtárik

Margin maximization in the hard-margin sense, proposed as feature elimination criterion by the MFE-LO method, is combined here with data radius utilization to further aim to lower generalization error, as several published bounds and…

Machine Learning · Statistics 2014-05-13 Yaman Aksu

We introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a robust and efficient optimization algorithm for smooth…

Machine Learning · Statistics 2024-10-15 Ibrahim Merad , Stéphane Gaïffas

Recently there are a considerable amount of work devoted to the study of the algorithmic stability and generalization for stochastic gradient descent (SGD). However, the existing stability analysis requires to impose restrictive assumptions…

Machine Learning · Computer Science 2020-06-16 Yunwen Lei , Yiming Ying

We develop the first active learning method for contextual linear optimization. Specifically, we introduce a label acquisition algorithm that sequentially decides whether to request the ``labels'' of feature samples from an unlabeled data…

Machine Learning · Computer Science 2025-01-31 Mo Liu , Paul Grigas , Heyuan Liu , Zuo-Jun Max Shen