English
Related papers

Related papers: Optimal oracle inequalities for model selection

200 papers

A popular technique for selecting and tuning machine learning estimators is cross-validation. Cross-validation evaluates overall model fit, usually in terms of predictive accuracy. In causal inference, the optimal choice of estimator…

Methodology · Statistics 2021-07-07 Dominik Rothenhäusler

In this work we investigate to which extent one can recover class probabilities within the empirical risk minimization (ERM) paradigm. The main aim of our paper is to extend existing results and emphasize the tight relations between…

Machine Learning · Computer Science 2020-07-22 Alexander Mey , Marco Loog

In this work, we establish risk bounds for the Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal works of Mendelson [Men15, Men18] on the analysis of ERM with…

Statistics Theory · Mathematics 2021-09-14 Abhishek Roy , Krishnakumar Balasubramanian , Murat A. Erdogdu

Given a finite collection of estimators or classifiers, we study the problem of model selection type aggregation, that is, we construct a new estimator or classifier, called aggregate, which is nearly as good as the best among them with…

Statistics Theory · Mathematics 2008-11-10 A. Juditsky , P. Rigollet , A. B. Tsybakov

We discuss the problem of risk estimation in the classification problem, with specific focus on finding distributions that maximize the confidence intervals of risk estimation. We derived simple analytic approximations for the maximum bias…

Machine Learning · Statistics 2014-08-15 Victor Nedelko

We consider the problem of statistical learning for the intensity of a counting process with covariates. In this context, we introduce an empirical risk, and prove risk bounds for the corresponding empirical risk minimizers. Then, we give…

Statistics Theory · Mathematics 2009-09-30 Stéphane Gaïffas , Agathe Guilloux

In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers. The classical approach to this problem is simply maximization of the expected margin, while more recent proposals consider…

Machine Learning · Statistics 2018-10-12 Matthew J. Holland

We consider the problem of estimating and optimizing utility-based shortfall risk (UBSR) of a loss, say $(Y - \hat Y)^2$, in the context of a regression problem. Empirical risk minimization with a UBSR objective is challenging since UBSR is…

Machine Learning · Computer Science 2025-06-12 Harish G. Ramaswamy , L. A. Prashanth

We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and on…

Machine Learning · Computer Science 2013-04-02 Sebastien Bubeck , Damien Ernst , Aurelien Garivier

The problem of ranking/ordering instances, instead of simply classifying them, has recently gained much attention in machine learning. In this paper we formulate the ranking problem in a rigorous statistical framework. The goal is to learn…

Statistics Theory · Mathematics 2016-08-16 Stéphan Clémençon , Gábor Lugosi , Nicolas Vayatis

Most classification methods provide either a prediction of class membership or an assessment of class membership probability. In the case of two-group classification the predicted probability can be described as "risk" of belonging to a…

Machine Learning · Statistics 2011-10-28 Yizhar Toren

Analyzing decision problems under uncertainty commonly relies on idealizing assumptions about the describability of the world, with the most prominent examples being the closed world and the small world assumption. Most assumptions are…

Methodology · Statistics 2025-12-08 Christoph Jansen , Georg Schollmeyer , Thomas Augustin , Julian Rodemann

The minimax risk is often considered as a gold standard against which we can compare specific statistical procedures. Nevertheless, as has been observed recently in robust and heavy-tailed estimation problems, the inherent reduction of the…

Statistics Theory · Mathematics 2024-07-08 Tianyi Ma , Kabir A. Verchand , Richard J. Samworth

We study the problem of model selection in batch policy optimization: given a fixed, partial-feedback dataset and $M$ model classes, learn a policy with performance that is competitive with the policy derived from the best model class. We…

Machine Learning · Computer Science 2021-12-24 Jonathan N. Lee , George Tucker , Ofir Nachum , Bo Dai

We build penalized least-squares estimators using the slope heuristic and resampling penalties. We prove oracle inequalities for the selected estimator with leading constant asymptotically equal to 1. We compare the practical performances…

Statistics Theory · Mathematics 2015-03-13 Matthieu Lerasle

Traditionally model averaging has been viewed as an alternative to model selection with the ultimate goal to incorporate the uncertainty associated with the model selection process in standard errors and confidence intervals by using a…

Methodology · Statistics 2021-03-05 Michael Schomaker , Christian Heumann

Conditional risk minimization arises in high-stakes decisions where risk must be assessed in light of side information, such as stressed economic conditions, specific customer profiles, or other contextual covariates. Constructing reliable…

Machine Learning · Statistics 2025-09-30 Xinqiao Xie , Jonathan Yu-Meng Li

The issue of constructing a risk minimizing hedge under an additional almost-surely type constraint on the shortfall profile is examined. Several classical risk minimizing problems are adapted to the new setting and solved. In particular,…

Pricing of Securities · Quantitative Finance 2015-12-11 Michał Barski

A dynamical model consists of a continuous self-map $T: \mathcal{X} \to \mathcal{X}$ of a compact state space $\mathcal{X}$ and a continuous observation function $f: \mathcal{X} \to \mathbb{R}$. This paper considers the fitting of a…

Statistics Theory · Mathematics 2018-01-24 Kevin McGoff , Andrew B. Nobel

In statistics and machine learning, when we train a fitted model on available data, we typically want to ensure that we are searching within a model class that contains at least one accurate model -- that is, we would like to ensure an…

Statistics Theory · Mathematics 2025-06-06 Manuel M. Müller , Yuetian Luo , Rina Foygel Barber