English
Related papers

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

200 papers

We study the algorithmic complexity of embeddings between bi-embeddable equivalence structures. We define the notions of computable bi-embeddable categoricity, (relative) $\Delta^0_\alpha$ bi-embeddable categoricity, and degrees of…

Logic · Mathematics 2021-03-16 Nikolay Bazhenov , Ekaterina Fokina , Dino Rossegger , Luca San Mauro

Classification is an important goal in many branches of mathematics. The idea is to describe the members of some class of mathematical objects, up to isomorphism or other important equivalence in terms of relatively simple invariants. Where…

Logic · Mathematics 2008-03-25 Wesley Calvert , Julia F. Knight

The fundamental theorem of statistical learning states that binary PAC learning is governed by a single parameter -- the Vapnik-Chervonenkis (VC) dimension -- which determines both learnability and sample complexity. Extending this to…

Machine Learning · Computer Science 2025-11-18 Alon Cohen , Liad Erez , Steve Hanneke , Tomer Koren , Yishay Mansour , Shay Moran , Qian Zhang

Goldwasser et al. (2021) recently proposed the setting of PAC verification, where a hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning objective is verified using an interactive proof. In this paper we…

Machine Learning · Statistics 2023-09-06 Saachi Mutreja , Jonathan Shafer

The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence. In an influential paper, Valiant recognised that the challenge of learning should be…

Artificial Intelligence · Computer Science 2023-06-12 Ionela G. Mocanu , Vaishak Belle , Brendan Juba

We investigate the computational properties of the spatial algebra RCC-5 which is a restricted version of the RCC framework for spatial reasoning. The satisfiability problem for RCC-5 is known to be NP-complete but not much is known about…

Artificial Intelligence · Computer Science 2009-09-25 P. Jonsson , T. Drakengren

In this paper, a mathematical theory of learning is proposed that has many parallels with information theory. We consider Vapnik's General Setting of Learning in which the learning process is defined to be the act of selecting a hypothesis…

Machine Learning · Computer Science 2014-05-08 Ibrahim Alabdulmohsin

A computable structure $\mathcal{A}$ is decidable if, given a formula $\varphi(\bar{x})$ of elementary first-order logic, and a tuple $\bar{a} \in \mathcal{A}$, we have a decision procedure to decide whether $\varphi$ holds of $\bar{a}$. We…

Logic · Mathematics 2017-02-23 Matthew Harrison-Trainor

An agnostic PAC learning algorithm finds a predictor that is competitive with the best predictor in a benchmark hypothesis class, where competitiveness is measured with respect to a given loss function. However, its predictions might be…

Machine Learning · Computer Science 2021-05-24 Guy N Rothblum , Gal Yona

The classical PAC sample complexity bounds are stated for any Empirical Risk Minimizer (ERM) and contain an extra logarithmic factor $\log(1/{\epsilon})$ which is known to be necessary for ERM in general. It has been recently shown by…

Machine Learning · Computer Science 2020-05-26 Olivier Bousquet , Steve Hanneke , Shay Moran , Nikita Zhivotovskiy

We study the primitive recursive analogue of computable categoricity spectra for various natural classes of structures. We show that these notions coincide for all relatively $\Delta_{2}^{0}$-categorical equivalence structures and linear…

Logic · Mathematics 2026-03-10 Nikolay Bazhenov , Heer Tern Koh , Keng Meng Ng

The empirical risk minimization (ERM) principle has been highly impactful in machine learning, leading both to near-optimal theoretical guarantees for ERM-based learning algorithms as well as driving many of the recent empirical successes…

Machine Learning · Computer Science 2025-02-25 Constantinos Daskalakis , Noah Golowich

The goal of the paper is to relate complexity measures associated with the evaluation of Boolean functions (certificate complexity, decision tree complexity) and learning dimensions used to characterize exact learning (teaching dimension,…

Machine Learning · Computer Science 2012-05-22 Sergiu Goschin

In a perfect category every object has a minimal projective resolution. We give a criterion for the category of modules over a categorygraded algebra to be perfect.

Category Theory · Mathematics 2016-02-09 Ana Paula Santana , Ivan Yudin

We introduce the notion of compactifiable classes -- these are classes of metrizable compact spaces that can be up to homeomorphic copies ``disjointly combined'' into one metrizable compact space. This is witnessed by so-called compact…

General Topology · Mathematics 2020-02-19 A. Bartoš , J. Bobok , J. van Mill , P. Pyrih , B. Vejnar

We consider equivalence relations and preorders complete for various levels of the arithmetical hierarchy under computable, component-wise reducibility. We show that implication in first order logic is a complete preorder for $\SI 1$, the…

Formal Languages and Automata Theory · Computer Science 2013-01-31 Egor Ianovski

We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have $k$ players and they want to learn a target function collaboratively, such that the learned function approximates the target…

Machine Learning · Computer Science 2018-10-15 Jiecao Chen , Qin Zhang , Yuan Zhou

Let $C$ be a smooth irreducible projective algebraic curve defined over the complex numbers. The notion of the Clifford index of $C$ was extended a few years ago to semistable bundles of any rank. Recent work has been focussed mainly on the…

Algebraic Geometry · Mathematics 2015-01-14 H. Lange , P. E. Newstead

We consider the problem of probably approximately correct (PAC) ranking $n$ items by adaptively eliciting subset-wise preference feedback. At each round, the learner chooses a subset of $k$ items and observes stochastic feedback indicating…

Machine Learning · Computer Science 2019-03-06 Aadirupa Saha , Aditya Gopalan

In this paper we will give a characterization of the learnability of forgiving 0-1 loss functions in the multiclass setting with effectively finite cardinality of the output and label space. To do this, we create a new combinatorial…

Machine Learning · Computer Science 2026-03-04 Jacob Trauger , Tyson Trauger , Ambuj Tewari