English
Related papers

Related papers: Scale-sensitive Psi-dimensions: the Capacity Measu…

200 papers

High dimensional data can have a surprising property: pairs of data points may be easily separated from each other, or even from arbitrary subsets, with high probability using just simple linear classifiers. However, this is more of a rule…

Machine Learning · Computer Science 2023-11-15 Oliver J. Sutton , Qinghua Zhou , Alexander N. Gorban , Ivan Y. Tyukin

We study VC-dimension of short formulas in Presburger Arithmetic, defined to have a bounded number of variables, quantifiers and atoms. We give both lower and upper bounds, which are tight up to a polynomial factor in the bit length of the…

Logic · Mathematics 2017-10-12 Danny Nguyen , Igor Pak

Statistical query (SQ) algorithms are algorithms that have access to an {\em SQ oracle} for the input distribution $D$ instead of i.i.d.~ samples from $D$. Given a query function $\phi:X \rightarrow [-1,1]$, the oracle returns an estimate…

Machine Learning · Computer Science 2017-04-18 Vitaly Feldman

We develop a formalism for constructing stochastic upper bounds on the expected full sample risk for supervised classification tasks via the Hilbert coresets approach within a transductive framework. We explicitly compute tight and…

Machine Learning · Computer Science 2021-03-30 Spencer Douglas , Piyush Kumar , R. K. Prasanth

This article conducts a large dimensional study of a simple yet quite versatile classification model, encompassing at once multi-task and semi-supervised learning, and taking into account uncertain labeling. Using tools from random matrix…

Machine Learning · Statistics 2024-02-22 Victor Leger , Romain Couillet

We consider inference on a scalar regression coefficient under a constraint on the magnitude of the control coefficients. A class of estimators based on a regularized propensity score regression is shown to exactly solve a tradeoff between…

Econometrics · Economics 2023-08-11 Timothy B. Armstrong , Michal Kolesár , Soonwoo Kwon

Pothos & Busemeyer's (P&B's) query about whether quantum probability can provide a foundation for the cognitive modeling embodies so many underlying implications that the subject is far from exhausted. In this brief commentary, however, I…

Neurons and Cognition · Quantitative Biology 2016-09-05 Alexandre de Castro

In this paper we revisit the risk bounds of the lasso estimator in the context of transductive and semi-supervised learning. In other terms, the setting under consideration is that of regression with random design under partial labeling.…

Statistics Theory · Mathematics 2016-11-09 Pierre C. Bellec , Arnak S. Dalalyan , Edwin Grappin , Quentin Paris

Increasingly deeper integration of HPC resources and QPUs unveils new challenges in computer architecture and engineering. As a consequence, dependability arises again as a concern encompassing resilience, reproducibility and security. The…

Quantum Physics · Physics 2026-03-10 Santiago Núñez-Corrales

In recent years, quantum machine learning (QML) has been actively used for various tasks, e.g., classification, reinforcement learning, and adversarial learning. However, these QML studies are unable to carry out complex tasks due to…

Quantum Physics · Physics 2022-11-15 Won Joon Yun , Hankyul Baek , Joongheon Kim

In this paper we demonstrate the only available scalable information bounds for quantities of interest of high dimensional probabilistic models. Scalability of inequalities allows us to (a) obtain uncertainty quantification bounds for…

Information Theory · Computer Science 2017-04-05 Markos A. Katsoulakis , Luc Rey-Bellet , Jie Wang

We bound the number of nearly orthogonal vectors with fixed VC-dimension over $\setpm^n$. Our bounds are of interest in machine learning and empirical process theory and improve previous bounds by Haussler. The bounds are based on a simple…

Combinatorics · Mathematics 2011-02-18 Lee-Ad Gottlieb , Leonid , Kontorovich , Elchanan Mossel

We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the…

Machine Learning · Statistics 2009-07-23 Andreas Maurer , Massimiliano Pontil

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Artificial Intelligence · Computer Science 2025-11-11 Maheep Chaudhary , Ian Su , Nikhil Hooda , Nishith Shankar , Julia Tan , Kevin Zhu , Ryan Lagasse , Vasu Sharma , Ashwinee Panda

The development and use of dimension reduction methods is prevalent in modern statistical literature. This paper reviews a class of dimension reduction techniques which aim to simultaneously select relevant predictors and find clusters…

Methodology · Statistics 2022-02-18 Suchit Mehrotra

The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the…

Many popular linear classifiers, such as logistic regression, boosting, or SVM, are trained by optimizing a margin-based risk function. Traditionally, these risk functions are computed based on a labeled dataset. We develop a novel…

Machine Learning · Computer Science 2010-07-23 Krishnakumar Balasubramanian , Pinar Donmez , Guy Lebanon

Supervised classification recognizes patterns in the data to separate classes of behaviours. Canonical solutions contain misclassification errors that are intrinsic to the numerical approximating nature of machine learning. The data analyst…

Machine Learning · Statistics 2023-09-12 Alberto Carlevaro , Teodoro Alamo , Fabrizio Dabbene , Maurizio Mongelli

The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence. Previous works provided…

Machine Learning · Computer Science 2025-03-12 Mathieu Bazinet , Valentina Zantedeschi , Pascal Germain

This paper takes a computational learning theory approach to a problem of linear systems identification. It is assumed that input signals have only a finite number k of frequency components, and systems to be identified have dimension no…

Optimization and Control · Mathematics 2007-05-23 Pirkko Kuusela , Daniel Ocone , Eduardo D. Sontag