English
Related papers

Related papers: PAC Learning, VC Dimension, and the Arithmetic Hie…

200 papers

Conceptual Scaling is a useful standard tool in Formal Concept Analysis and beyond. Its mathematical theory, as elaborated in the last chapter of the FCA monograph, still has room for improvement. As it stands, even some of the basic…

Machine Learning · Computer Science 2023-07-25 Bernhard Ganter , Tom Hanika , Johannes Hirth

Multi-index models - functions which only depend on the covariates through a non-linear transformation of their projection on a subspace - are a useful benchmark for investigating feature learning with neural nets. This paper examines the…

Machine Learning · Computer Science 2025-11-13 Emanuele Troiani , Yatin Dandi , Leonardo Defilippis , Lenka Zdeborová , Bruno Loureiro , Florent Krzakala

The existence of evasion attacks during the test phase of machine learning algorithms represents a significant challenge to both their deployment and understanding. These attacks can be carried out by adding imperceptible perturbations to…

Machine Learning · Statistics 2018-06-07 Daniel Cullina , Arjun Nitin Bhagoji , Prateek Mittal

How many bits of information are required to PAC learn a class of hypotheses of VC dimension $d$? The mathematical setting we follow is that of Bassily et al. (2018), where the value of interest is the mutual information…

Machine Learning · Computer Science 2018-04-20 Ido Nachum , Jonathan Shafer , Amir Yehudayoff

We classify the computability-theoretic complexity of two index sets of classes of first-order theories: We show that the property of being an $\aleph_0$-categorical theory is $\Pi^0_3$-complete; and the property of being an Ehrenfeucht…

Logic · Mathematics 2007-05-23 Steffen Lempp , Theodore A. Slaman

A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect,…

Machine Learning · Computer Science 2007-05-23 Nick Palmer , Paul W. Goldberg

This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the…

Machine Learning · Computer Science 2016-09-13 Steve Hanneke

Computably enumerable equivalence relations (ceers) received a lot of attention in the literature. The standard tool to classify ceers is provided by the computable reducibility $\leq_c$. This gives rise to a rich degree-structure. In this…

Logic · Mathematics 2021-03-19 Nikolay Bazhenov , Manat Mustafa , Luca San Mauro , Andrea Sorbi , Mars Yamaleev

Networked dynamical systems are widely used as formal models of real-world cascading phenomena, such as the spread of diseases and information. Prior research has addressed the problem of learning the behavior of an unknown dynamical system…

The present paper constructs three new systems of clarithmetic (arithmetic based on computability logic --- see http://www.cis.upenn.edu/~giorgi/cl.html): CLA8, CLA9 and CLA10. System CLA8 is shown to be sound and extensionally complete…

Logic in Computer Science · Computer Science 2012-11-21 Giorgi Japaridze

We generalize the PAC (probably approximately correct) learning model to the quantum world by generalizing the concepts from classical functions to quantum processes, defining the problem of \emph{PAC learning quantum process}, and study…

Quantum Physics · Physics 2021-05-20 Kai-Min Chung , Han-Hsuan Lin

Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class $H$, and often leads to learners with simple algorithmic forms (e.g. empirical risk minimization (ERM), structural risk…

Machine Learning · Computer Science 2025-12-10 Julian Asilis , Siddartha Devic , Shaddin Dughmi , Vatsal Sharan , Shang-Hua Teng

Precision and Recall are fundamental metrics in machine learning tasks where both accurate predictions and comprehensive coverage are essential, such as in multi-label learning, language generation, medical studies, and recommender systems.…

Machine Learning · Computer Science 2025-10-27 Lee Cohen , Yishay Mansour , Shay Moran , Han Shao

In many learning theory problems, a central role is played by a hypothesis class: we might assume that the data is labeled according to a hypothesis in the class (usually referred to as the realizable setting), or we might evaluate the…

Machine Learning · Computer Science 2022-11-17 Lunjia Hu , Charlotte Peale

We adapt the classical notion of learning from text to computable structure theory. Our main result is a model-theoretic characterization of the learnability from text for classes of structures. We show that a family of structures is…

The main goal of this article is to convince you, the reader, that supervised learning in the Probably Approximately Correct (PAC) model is closely related to -- of all things -- bipartite matching! En-route from PAC learning to bipartite…

Machine Learning · Computer Science 2025-05-06 Shaddin Dughmi

We consider the long-standing question of finding a parameter of a class of probability distributions that characterizes its PAC learnability. We provide a rather surprising answer - no such parameter exists. Our techniques allow us to show…

Machine Learning · Computer Science 2023-04-25 Tosca Lechner , Shai Ben-David

We initiate the study of computable presentations of real and complex C*-algebras under the program of effective metric structure theory. With the group situation as a model, we develop corresponding notions of recursive presentations and…

Logic · Mathematics 2023-04-17 Alec Fox

Given a countable mathematical structure, its Scott sentence is a sentence of the infinitary logic $\mathcal{L}_{\omega_1 \omega}$ that characterizes it among all countable structures. We can measure the complexity of a structure by the…

Logic · Mathematics 2025-11-07 Rachael Alvir , Barbara Csima , Matthew Harrison-Trainor

Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest is the sample complexity: the number of samples required to…

Machine Learning · Computer Science 2008-07-10 David Soloveichik