English
Related papers

Related papers: Playing Billiard in Version Space

200 papers

We introduce the concepts of rotation numbers and rotation vectors for billiard maps. Our approach is based on the birkhoff ergodic theorem. We anticipate that it will be useful, in particular, for the purpose of establishing the…

Dynamical Systems · Mathematics 2009-02-25 Eugene Gutkin

After experimenting with a number of non-probabilistic methods for dealing with uncertainty many researchers reaffirm a preference for probability methods [1] [2], although this remains controversial. The importance of being able to form…

Artificial Intelligence · Computer Science 2013-04-11 Thomas Slack

Hit-and-Run is known to be one of the best random sampling algorithms, its mixing time is polynomial in dimension. Nevertheless, in practice the number of steps required to achieve uniformly distributed samples is rather high. We propose…

Optimization and Control · Mathematics 2014-02-13 Elena Gryazina , Boris Polyak

General Probabilistic Theories provide the most general mathematical framework for the theory of probability in an operationally natural manner, and generalize classical and quantum theories. In this article, we study state-discrimination…

Quantum Physics · Physics 2010-09-15 Koji Nuida , Gen Kimura , Takayuki Miyadera

In game theory, players have continuous expected payoff functions and can use fixed point theorems to locate equilibria. This optimization method requires that players adopt a particular type of probability measure space. Here, we introduce…

Optimization and Control · Mathematics 2007-05-23 Michael J. Gagen , Kae Nemoto

A widely used method to create a continuous representation of a discrete data-set is regression analysis. When the regression model is not based on a mathematical description of the physics underlying the data, heuristic techniques play a…

Statistics Theory · Mathematics 2013-07-18 Giovanni Mana , Paolo Alberto Giuliano Albo , Simona Lago

In this paper, we extend the transfer learning classification framework from regression function-based methods to decision rules. We propose a novel methodology for modeling posterior drift through Bayes decision rules. By exploiting the…

Machine Learning · Statistics 2025-08-29 Xiaohan Wang , Yang Ning

Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time.…

Machine Learning · Statistics 2011-09-22 Christos Dimitrakakis

We consider polygonal billiards with collisions contracting the reflection angle towards the normal to the boundary of the table. In previous work, we proved that such billiards has a finite number of ergodic SRB measures supported on…

Dynamical Systems · Mathematics 2019-10-29 Gianluigi Del Magno , João Lopes Dias , Pedro Duarte , José Pedro Gaivão

This paper shows how the Bayesian network paradigm can be used in order to solve combinatorial optimization problems. To do it some methods of structure learning from data and simulation of Bayesian networks are inserted inside Estimation…

Artificial Intelligence · Computer Science 2013-01-18 Pedro Larrañaga , Ramon Etxeberria , Jose A. Lozano , Jose M. Pena

A common problem faced in statistical inference is drawing conclusions from paired comparisons, in which two objects compete and one is declared the victor. A probabilistic approach to such a problem is the Bradley-Terry model, first…

Applications · Statistics 2017-12-19 Gabriel C. Phelan , John T. Whelan

We characterize the optimal reward functions (scoring rules) that incentivize an agent to acquire information and report it truthfully to the principal. The optimal scoring rules let the agent make a simple binary bet in single-dimensional…

Computer Science and Game Theory · Computer Science 2025-10-03 Jason D. Hartline , Yingkai Li , Liren Shan , Yifan Wu

It is well understood that Bayesian decision theory and average case analysis are essentially identical. However, if one is interested in performing uncertainty quantification for a numerical task, it can be argued that standard approaches…

Methodology · Statistics 2020-07-16 Chris. J. Oates , Jon Cockayne , Dennis Prangle , T. J. Sullivan , Mark Girolami

We consider a class of random billiards in a tube, where reflection angles at collisions with the boundary of the tube are random variables rather than deterministic (and elastic) quantities. We obtain a (non-standard) Central Limit Theorem…

Dynamical Systems · Mathematics 2025-07-21 Henk Bruin , Niels Kolenbrander , Dalia Terhesiu

Bayesian optimization through Gaussian process regression is an effective method of optimizing an unknown function for which every measurement is expensive. It approximates the objective function and then recommends a new measurement point…

Machine Learning · Statistics 2017-05-17 Hildo Bijl , Thomas B. Schön , Jan-Willem van Wingerden , Michel Verhaegen

This paper introduces a novel algorithm for two-player deterministic games with perfect information, which we call PROBS (Predict Results of Beam Search). Unlike existing methods that predominantly rely on Monte Carlo Tree Search (MCTS) for…

Artificial Intelligence · Computer Science 2024-04-26 Sergey Pastukhov

A Bayesian network is a widely used probabilistic graphical model with applications in knowledge discovery and prediction. Learning a Bayesian network (BN) from data can be cast as an optimization problem using the well-known…

Artificial Intelligence · Computer Science 2018-11-14 Zhenyu A. Liao , Charupriya Sharma , James Cussens , Peter van Beek

Recent decades have seen an interest in prediction problems for which Bayesian methodology has been used ubiquitously. Sampling from or approximating the posterior predictive distribution in a Bayesian model allows one to make inferential…

Machine Learning · Statistics 2017-09-12 Giri Gopalan

In this paper we study the ergodic properties of mathematical billiards describing the uniform motion of a point in a flat torus from which finitely many, pairwise disjoint, tubular neighborhoods of translated subtori (the so called…

Dynamical Systems · Mathematics 2010-08-12 Nandor Simanyi

Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal…

Machine Learning · Computer Science 2015-03-20 Arthur Guez , David Silver , Peter Dayan
‹ Prev 1 2 3 10 Next ›