English
Related papers

Related papers: Local Risk Bounds for Statistical Aggregation

200 papers

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be affected by the adversary during testing. The learner's goal is to build a…

Machine Learning · Computer Science 2022-07-04 Idan Attias , Aryeh Kontorovich , Yishay Mansour

We consider the Bayesian optimal filtering problem: i.e. estimating some conditional statistics of a latent time-series signal from an observation sequence. Classical approaches often rely on the use of assumed or estimated transition and…

Machine Learning · Statistics 2023-03-16 Adrian N. Bishop , Edwin V. Bonilla

We present a novel notion of complexity that interpolates between and generalizes some classic existing complexity notions in learning theory: for estimators like empirical risk minimization (ERM) with arbitrary bounded losses, it is upper…

Machine Learning · Computer Science 2017-10-24 Peter D. Grünwald , Nishant A. Mehta

We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bregman divergence associated with log-partition function of…

Machine Learning · Computer Science 2023-07-14 Sayak Ray Chowdhury , Patrick Saux , Odalric-Ambrym Maillard , Aditya Gopalan

This work establishes a novel link between the problem of PAC-learning high-dimensional graphical models and the task of (efficient) counting and sampling of graph structures, using an online learning framework. We observe that if we apply…

Machine Learning · Computer Science 2025-11-14 Arnab Bhattacharyya , Sutanu Gayen , Philips George John , Sayantan Sen , N. V. Vinodchandran

Analysing statistical properties of neural networks is a central topic in statistics and machine learning. However, most results in the literature focus on the properties of the neural network minimizing the training error. The goal of this…

Statistics Theory · Mathematics 2022-02-04 Laura Tinsi , Arnak S. Dalalyan

Machine learning typically presupposes classical probability theory which implies that aggregation is built upon expectation. There are now multiple reasons to motivate looking at richer alternatives to classical probability theory as a…

Machine Learning · Computer Science 2024-01-30 Christian Fröhlich , Robert C. Williamson

We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all…

Machine Learning · Computer Science 2020-06-23 Ben London

We discuss CLT for the global and local linear statistics of random matrices from classical compact groups. The main part of our proofs are certain combinatorial identities much in the spirit of works by Kac and Spohn.

Probability · Mathematics 2007-05-23 Alexander Soshnikov

We introduce a general random model of a combinatorial optimization problem with geometric structure that encapsulates both linear programming and integer linear programming. Let $Q$ be a bounded set called the feasible set, $E$ be an…

Probability · Mathematics 2024-07-25 Dylan J. Altschuler

In the same spirit as Tsybakov (2003), we define the optimality of an aggregation procedure in the problem of classification. Using an aggregate with exponential weights, we obtain an optimal rate of convex aggregation for the hinge risk…

Statistics Theory · Mathematics 2007-12-04 Guillaume Lecué

Linear Autoencoders (LAEs) have shown strong performance in state-of-the-art recommender systems. However, this success remains largely empirical, with limited theoretical understanding. In this paper, we investigate the generalizability --…

Machine Learning · Statistics 2025-12-16 Ruixin Guo , Ruoming Jin , Xinyu Li , Yang Zhou

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution $p$, extensive research has established optimal bounds for uniformity testing,…

Machine Learning · Computer Science 2024-12-03 Maryam Aliakbarpour , Piotr Indyk , Ronitt Rubinfeld , Sandeep Silwal

A refinement of Bennett's inequality is introduced which is strictly tighter than the classical bound. The new bound establishes the convergence of the average of independent random variables to its expected value. It also carefully…

Statistics Theory · Mathematics 2018-04-17 Tony Jebara

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. When the input…

Machine Learning · Statistics 2010-07-06 Jean-Yves Audibert , Olivier Catoni

In this paper we penetrate and extend the notion of local constancy in graphical models that has been introduced by Honorio et al. (2009). We propose Neighborhood-Fused Lasso, a method for model selection in high-dimensional graphical…

Methodology · Statistics 2014-11-03 Apratim Ganguly , Wolfgang Polonik

Deep neural networks (DNNs) are vulnerable to adversarial attacks. It is found empirically that adversarially robust generalization is crucial in establishing defense algorithms against adversarial attacks. Therefore, it is interesting to…

Machine Learning · Computer Science 2023-10-31 Jiancong Xiao , Ruoyu Sun , Zhi- Quan Luo

A key challenge for decision makers when incorporating black box machine learned models into practice is being able to understand the predictions provided by these models. One proposed set of methods is training surrogate explainer models…

Machine Learning · Computer Science 2020-11-17 Qiaomei Li , Rachel Cummings , Yonatan Mintz

In cluster analysis interest lies in probabilistically capturing partitions of individuals, items or observations into groups, such that those belonging to the same group share similar attributes or relational profiles. Bayesian posterior…

Methodology · Statistics 2017-03-23 Riccardo Rastelli , Nial Friel

We derive generic information-theoretic and PAC-Bayesian generalization bounds involving an arbitrary convex comparator function, which measures the discrepancy between the training and population loss. The bounds hold under the assumption…

Machine Learning · Computer Science 2024-02-22 Fredrik Hellström , Benjamin Guedj
‹ Prev 1 3 4 5 6 7 10 Next ›