English
Related papers

Related papers: Learning Equivalence Relations on Polish Spaces

200 papers

In the last years there has been a growing interest in the study of learning problems associated with algebraic structures. The framework we use models the scenario in which a learner is given larger and larger fragments of a structure from…

Algorithmic learning theory traditionally studies the learnability of effective infinite binary sequences (reals), while recent work by [Vitanyi and Chater, 2017] and [Bienvenu et al., 2014] has adapted this framework to the study of…

Logic · Mathematics 2018-07-17 George Barmpalias , Nan Fang , Frank Stephan

We demonstrate that a wide array of machine learning algorithms are specific instances of one single paradigm: reciprocal learning. These instances range from active learning over multi-armed bandits to self-training. We show that all these…

Machine Learning · Statistics 2024-11-05 Julian Rodemann , Christoph Jansen , Georg Schollmeyer

Conversation is like an intricate partner dance and behavioral convergence, or the similarity in observable behaviors of partners over time, can lead to shared understanding, changed beliefs and increased rapport. This article describes a…

Computers and Society · Computer Science 2016-08-11 Tanmay Sinha

We associate to every action of a Polish group on a standard probability space a Polish group that we call the orbit full group. For discrete groups, we recover the well-known full groups of pmp equivalence relations equipped with the…

Group Theory · Mathematics 2014-11-24 Alessandro Carderi , François Le Maître

In this paper we further develop the theory of canonical approximations of Polishable subgroups of Polish groups, building on previous work of Solecki and Farah--Solecki. In particular, we obtain a characterization of such canonical…

Logic · Mathematics 2022-02-07 Martino Lupini

We study the class of Borel equivalence relations under continuous reducibility. In particular , we characterize when a Borel equivalence relation with countable equivalence classes is $\Sigma$ 0 $\xi$ (or $\Pi$ 0 $\xi$). We characterize…

Logic · Mathematics 2018-05-30 Dominique Lecomte

Working in the framework of Borel reducibility, we study various notions of embeddability between groups. We prove that the embeddability between countable groups, the topological embeddability between (discrete) Polish groups, and the…

Logic · Mathematics 2018-02-08 Filippo Calderoni , Luca Motto Ros

Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes…

Computation and Language · Computer Science 2014-12-09 Danushka Bollegala , Takanori Maehara , Yuichi Yoshida , Ken-ichi Kawarabayashi

We provide a complete classification, up to order-isomorphism, of all possible Wadge hierarchies on zero-dimensional Polish spaces using (essentially) countable ordinals as complete invariants. We also observe that although our assignment…

Logic · Mathematics 2023-05-17 Raphaël Carroy , Luca Motto Ros , Salvatore Scamperti

Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize…

Robotics · Computer Science 2017-07-25 Oier Mees , Nichola Abdo , Mladen Mazuran , Wolfram Burgard

A variation of the Scott analysis of countable structures is applied to actions of non-Archimedean TSI Polish groups acting continuously on a Polish spaces. We give results on the potential Borel complexity spectrum of such groups, and…

Logic · Mathematics 2023-04-05 Shaun Allison

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules,…

Artificial Intelligence · Computer Science 2019-01-11 Zhi-Xuan Tan , Jake Brawer , Brian Scassellati

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

Robotics · Computer Science 2023-03-20 Andreea Bobu , Yi Liu , Rohin Shah , Daniel S. Brown , Anca D. Dragan

We develop a unified framework for locating natural properties of algebraic and analytic structures within the Borel hierarchy. Objects are presented as quotients of a universal generator and definability is read directly from the quotient…

Logic · Mathematics 2026-04-20 Tomasz Kania

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often…

Machine Learning · Computer Science 2022-10-20 Stephen Zhao , Chris Lu , Roger Baker Grosse , Jakob Nicolaus Foerster

In language learning in the limit we investigate computable devices (learners) learning formal languages. Through the years, many natural restrictions have been imposed on the studied learners. As such, monotonic restrictions always enjoyed…

Machine Learning · Computer Science 2020-10-20 Vanja Doskoč , Timo Kötzing

Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…

Computation and Language · Computer Science 2025-02-19 Tianyang Xu , Tatsuki Kuribayashi , Yohei Oseki , Ryan Cotterell , Alex Warstadt

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

Optimization and Control · Mathematics 2019-05-29 Joseph E. Gaudio , Travis E. Gibson , Anuradha M. Annaswamy , Michael A. Bolender

While most research in Gold-style learning focuses on learning formal languages, we consider the identification of computable structures, specifically equivalence structures. In our core model the learner gets more and more information…

Logic · Mathematics 2019-02-22 Ekaterina Fokina , Timo Kötzing , Luca San Mauro