English
Related papers

Related papers: A note on the impossibility of conditional PAC-eff…

200 papers

Machine learning researchers and practitioners steadily enlarge the multitude of successful learning models. They achieve this through in-depth theoretical analyses and experiential heuristics. However, there is no known general-purpose…

Computational Complexity · Computer Science 2023-10-18 Matthias C. Caro

The PAC-Bayesian approach is a powerful set of techniques to derive non- asymptotic risk bounds for random estimators. The corresponding optimal distribution of estimators, usually called the Gibbs posterior, is unfortunately intractable.…

Machine Learning · Statistics 2015-06-16 Pierre Alquier , James Ridgway , Nicolas Chopin

We discuss necessary conditions for a PAC-Bayes bound to provide a meaningful generalisation guarantee. Our analysis reveals that the optimal generalisation guarantee depends solely on the distribution of the risk induced by the prior…

Machine Learning · Statistics 2025-03-12 Antoine Picard-Weibel , Eugenio Clerico , Roman Moscoviz , Benjamin Guedj

Mathematical optimization offers highly-effective tools for finding solutions for problems with well-defined goals, notably scheduling. However, optimization solvers are often unexplainable black boxes whose solutions are inaccessible to…

Artificial Intelligence · Computer Science 2019-02-21 Kristijonas Čyras , Dimitrios Letsios , Ruth Misener , Francesca Toni

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

We spell out the paradigm of exact conditioning as an intuitive and powerful way of conditioning on observations in probabilistic programs. This is contrasted with likelihood-based scoring known from languages such as Stan. We study exact…

Programming Languages · Computer Science 2023-12-29 Dario Stein , Sam Staton

Equilibrium computation in markets usually considers settings where player valuation functions are known. We consider the setting where player valuations are unknown; using a PAC learning-theoretic framework, we analyze some classes of…

Computer Science and Game Theory · Computer Science 2021-09-10 Vignesh Viswanathan , Omer Lev , Neel Patel , Yair Zick

Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic frameworks. A key challenge is that formal solvers lack commonsense world knowledge,…

Artificial Intelligence · Computer Science 2026-05-11 Joseph Cotnareanu , Chiara Roverato , Han Zhou , Didier Chetelat , Yingxue Zhang , Mark Coates

A central problem in sequential decision making is to develop algorithms that are practical and computationally efficient, yet support the use of flexible, general-purpose models. Focusing on the contextual bandit problem, recent progress…

Machine Learning · Computer Science 2022-07-14 Yinglun Zhu , Dylan J. Foster , John Langford , Paul Mineiro

Propositional logics in general, considered as a set of sentences, can be undecidable even if they have "nice" representations, e.g., are given by a calculus. Even decidable propositional logics can be computationally complex (e.g., already…

Logic · Mathematics 2019-08-06 Matthias Baaz , Richard Zach

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the…

A controversial test for Large Language Models concerns the ability to discern possible from impossible language. While some evidence attests to the models' sensitivity to what crosses the limits of grammatically impossible language, this…

Computation and Language · Computer Science 2025-09-19 Evelina Leivada , Raquel Montero , Paolo Morosi , Natalia Moskvina , Tamara Serrano , Marcel Aguilar , Fritz Guenther

We phrase parsing with context-free expressions as a type inhabitation problem where values are parse trees and types are context-free expressions. We first show how containment among context-free and regular expressions can be reduced to a…

Formal Languages and Automata Theory · Computer Science 2017-08-25 Martin Sulzmann , Peter Thiemann

We study the problem of PAC learning halfspaces in the reliable agnostic model of Kalai et al. (2012). The reliable PAC model captures learning scenarios where one type of error is costlier than the others. Our main positive result is a new…

Machine Learning · Computer Science 2024-11-19 Ilias Diakonikolas , Lisheng Ren , Nikos Zarifis

Motivated by the pervasiveness of strong inapproximability results for Max-CSPs, we introduce a relaxed notion of an approximate solution of a Max-CSP. In this relaxed version, loosely speaking, the algorithm is allowed to replace the…

Computational Complexity · Computer Science 2012-04-26 Per Austrin , Johan Håstad

We provide a logical framework in which a resource-bounded agent can be seen to perform approximations of probabilistic reasoning. Our main results read as follows. First we identify the conditions under which propositional probability…

Logic in Computer Science · Computer Science 2022-05-09 Paolo Baldi , Hykel Hosni

We make three related contributions motivated by the challenge of training stochastic neural networks, particularly in a PAC-Bayesian setting: (1) we show how averaging over an ensemble of stochastic neural networks enables a new class of…

Machine Learning · Computer Science 2021-12-16 Felix Biggs , Benjamin Guedj

"No free lunch" results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling. Some models are expensive (strong assumptions, such as as subgaussian tails),…

Machine Learning · Computer Science 2021-12-16 Benjamin Guedj , Louis Pujol

When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for…

Artificial Intelligence · Computer Science 2021-02-23 Federico Cerutti , Lance M. Kaplan , Angelika Kimmig , Murat Sensoy

We develop a new method for generating prediction sets that combines the flexibility of conformal methods with an estimate of the conditional distribution $P_{Y \mid X}$. Existing methods, such as conformalized quantile regression and…

Machine Learning · Statistics 2024-10-10 Vincent Plassier , Alexander Fishkov , Mohsen Guizani , Maxim Panov , Eric Moulines
‹ Prev 1 3 4 5 6 7 10 Next ›