English
Related papers

Related papers: Generalized Interacting Urn Models

200 papers

We introduce the notion of nonuniform coercion, which is the promotion of a value of one type to an enriched value of a different type via a nonuniform procedure. Nonuniform coercions are a generalization of the (uniform) coercions known in…

Logic in Computer Science · Computer Science 2011-03-18 Claudio Sacerdoti Coen , Enrico Tassi

When engagement with a randomized trial is driven by factors that affect the outcome or when trial engagement directly affects the outcome independent of treatment, the average treatment effect among trial participants is unlikely to…

Reinforcement learning can learn amortised design policies for designing sequences of experiments. However, current amortised methods rely on estimators of expected information gain (EIG) that require an exponential number of samples on the…

Machine Learning · Computer Science 2024-02-06 Tom Blau , Iadine Chades , Amir Dezfouli , Daniel Steinberg , Edwin V. Bonilla

Conjoint experiments randomize multidimensional profiles, offering a powerful design for recovering structural preference parameters -- including marginal rates of substitution, willingness to pay, and the distribution of preferences across…

Methodology · Statistics 2026-05-26 Avidit Acharya , Jens Hainmueller , Yiqing Xu

In this work we discuss two urn models with general weight sequences $(A,B)$ associated to them, $A=(\alpha_n)_{n\in\N}$ and $B=(\beta_m)_{m\in\N}$, generalizing two well known P\'olya-Eggenberger urn models, namely the so-called sampling…

Combinatorics · Mathematics 2010-05-11 Markus Kuba

We investigate equilibrium statistical properties of urn models with disorder. Two urn models are proposed; one belongs to the Ehrenfest class, and the other corresponds to the Monkey class. These models are introduced from the view point…

Physics and Society · Physics 2008-02-27 Jun-ichi Inoue , Jun Ohkubo

We consider the problem of inferring a graphical Potts model on a population of variables, with a non-uniform number of Potts colors (symbols) across variables. This inverse Potts problem generally involves the inference of a large number…

To improve nonparametric estimates of lifetime distributions, we propose using the increasing odds rate (IOR) model as an alternative to other popular, but more restrictive, ``adverse ageing'' models, such as the increasing hazard rate one.…

Methodology · Statistics 2022-12-13 Tommaso Lando , Idir Arab , Paulo Eduardo Oliveira

We consider a coupled Polya's urn scheme for social dynamics on networks. Agents hold continuum-valued opinions on a two-state issue and randomly converse with their neighbors on a graph, agreeing on one of the two states. The probability…

Probability · Mathematics 2023-07-04 Andrew Melchionna

The framework of reinforcement learning or optimal control provides a mathematical formalization of intelligent decision making that is powerful and broadly applicable. While the general form of the reinforcement learning problem enables…

Machine Learning · Computer Science 2018-05-22 Sergey Levine

Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. Following prior work that relates cross-linguistic tendencies to biases in learning, we ask…

Computation and Language · Computer Science 2026-04-30 Andrea Silvi , Ponrawee Prasertsom , Jennifer Culbertson , Devdatt Dubhashi , Moa Johansson , Kenny Smith

Exponential random graph models (ERGMs) are a widely used framework for network data, enabling hypothesis testing on the structural mechanisms underlying observed networks. Bayesian ERGMs provide principled uncertainty quantification and…

Methodology · Statistics 2026-05-26 Alberto Caimo , Isabella Gollini

We present a novel model for the effect of echo chambers, filter bubbles, and reinforcement on election results. Our model extends the well known voter model with zealots to include reinforcement. We analyze the behaviour of the model,…

Physics and Society · Physics 2020-07-09 Johannes Müller , Volker Hösel , Aurélien Tellier

This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both…

Machine Learning · Computer Science 2012-08-07 Riad Akrour , Marc Schoenauer , Michèle Sebag

In this paper we extend the framework of evolutionary inspection game put forward recently by the author and coworkers to a large class of conflict interactions dealing with the pressure executed by the major player (or principal) on the…

Optimization and Control · Mathematics 2022-05-03 Vassili Kolokoltsov

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into…

Machine Learning · Computer Science 2018-09-07 David Ha , Jürgen Schmidhuber

We derive an asymptotic power function for a likelihood-based test for interaction in a regression model, with possibly misspecified alternative distribution. This allows a general investigation of types of interactions which are poorly or…

Statistics Theory · Mathematics 2007-11-27 Juxin Liu , Paul Gustafson

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

Machine Learning · Computer Science 2017-11-28 Peter Henderson , Wei-Di Chang , Pierre-Luc Bacon , David Meger , Joelle Pineau , Doina Precup

We introduce a log-gas model that is a generalization of a random matrix ensemble with an additional interaction, whose strength depends on a parameter $\gamma$. The equilibrium density is computed by numerically solving the Riemann-Hilbert…

Disordered Systems and Neural Networks · Physics 2020-06-11 Swapnil Yadav , Kazi Alam , K. A. Muttalib , Dong Wang

GNN-based approaches for learning general policies across planning domains are limited by the expressive power of $C_2$, namely; first-order logic with two variables and counting. This limitation can be overcame by transitioning to…

Artificial Intelligence · Computer Science 2025-02-19 Simon Ståhlberg , Blai Bonet , Hector Geffner