English
Related papers

Related papers: On the Foundations of Universal Sequence Predictio…

200 papers

We present a computational framework for estimating the uncertainty in the numerical solution of linearized infinite-dimensional statistical inverse problems. We adopt the Bayesian inference formulation: given observational data and their…

Numerical Analysis · Mathematics 2013-08-07 Tan Bui-Thanh , Omar Ghattas , James Martin , Georg Stadler

Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the…

We study sequential prediction of real-valued, arbitrary and unknown sequences under the squared error loss as well as the best parametric predictor out of a large, continuous class of predictors. Inspired by recent results from…

Machine Learning · Computer Science 2014-01-24 N. Denizcan Vanli , Suleyman S. Kozat

We investigate Bayesian predictive inference for finite population quantities when there are unequal probabilities of selection. Only limited information about the sample design is available; i.e., only the first-order selection…

Methodology · Statistics 2018-04-10 Junheng Ma , Joe Sedransk , Balgobin Nandram , Lu Chen

We consider the Bayesian optimal filtering problem: i.e. estimating some conditional statistics of a latent time-series signal from an observation sequence. Classical approaches often rely on the use of assumed or estimated transition and…

Machine Learning · Statistics 2023-03-16 Adrian N. Bishop , Edwin V. Bonilla

We devise a fairly general sufficient condition ensuring that the endomorphism monoid of a countably infinite ultrahomogeneous structure (i.e. a Fra\"{\i}ss\'{e} limit) embeds all countable semigroups. This approach provides us not only…

Group Theory · Mathematics 2014-03-10 Igor Dolinka , Dragan Mašulović

While Kolmogorov's probability axioms are widely recognized, it is less well known that in an often-overlooked 1930 note, Kolmogorov proposed an axiomatic framework for a unifying concept of the mean -- referred to as regular means. This…

Statistics Theory · Mathematics 2026-01-15 Miguel de Carvalho

We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning. This is accomplished by a probabilistic model-based approach…

We study the problem of sequentially predicting properties of a probabilistic model and its next outcome over an infinite horizon, with the goal of ensuring that the predictions incur only finitely many errors with probability 1. We…

Statistics Theory · Mathematics 2024-02-08 Changlong Wu , Narayana Santhanam

With infinitely many high-quality data points, infinite computational power, an infinitely large foundation model with a perfect training algorithm and guaranteed zero generalization error on the pretext task, can the model be used for…

Artificial Intelligence · Computer Science 2026-04-27 Yang Yuan

Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions. We propose a novel hierarchical model for…

Machine Learning · Computer Science 2015-03-10 Ehsan Shareghi , Gholamreza Haffari , Trevor Cohn , Ann Nicholson

A universal sequence for a group or semigroup $S$ is a sequence of words $w_1, w_2, \ldots$ such that for any sequence $s_1, s_2, \ldots\in S$, the equations $w_n = s_n$, $n\in \mathbb{N}$, can be solved simultaneously in $S$. For example,…

Group Theory · Mathematics 2019-09-24 James Hyde , Julius Jonušas , James D. Mitchell , Yann H. Péresse

Modern machine learning tasks often require considering not just one but multiple objectives. For example, besides the prediction quality, this could be the efficiency, robustness or fairness of the learned models, or any of their…

Machine Learning · Computer Science 2022-08-30 Peter Súkeník , Christoph H. Lampert

Much is now known about the consistency of Bayesian updating on infinite-dimensional parameter spaces with independent or Markovian data. Necessary conditions for consistency include the prior putting enough weight on the correct…

Statistics Theory · Mathematics 2022-03-18 Cosma Rohilla Shalizi

Given i.i.d. data from an unknown distribution, we consider the problem of predicting future items. An adaptive way to estimate the probability density is to recursively subdivide the domain to an appropriate data-dependent granularity. A…

Probability · Mathematics 2009-12-30 Marcus Hutter

This paper illustrates the richness of the concept of regular sets of time bounds and demonstrates its application to problems of computational complexity. There is a universe of bounds whose regular subsets allow to represent several time…

Computational Complexity · Computer Science 2013-09-24 Armin Hemmerling

Tarski gave a general semantics for deductive reasoning: a formula a may be deduced from a set A of formulas iff a holds in all models in which each of the elements of A holds. A more liberal semantics has been considered: a formula a may…

Artificial Intelligence · Computer Science 2007-05-23 Daniel Lehmann

An a priori semimeasure (also known as "algorithmic probability" or "the Solomonoff prior" in the context of inductive inference) is defined as the transformation, by a given universal monotone Turing machine, of the uniform measure on the…

Statistics Theory · Mathematics 2016-06-29 Tom F. Sterkenburg

Although being a crucial question for the development of machine learning algorithms, there is still no consensus on how to compare classifiers over multiple data sets with respect to several criteria. Every comparison framework is…

Machine Learning · Statistics 2023-07-06 Christoph Jansen , Malte Nalenz , Georg Schollmeyer , Thomas Augustin

Modelling functions of sets, or equivalently, permutation-invariant functions, is a long-standing challenge in machine learning. Deep Sets is a popular method which is known to be a universal approximator for continuous set functions. We…

Machine Learning · Computer Science 2021-07-06 Edward Wagstaff , Fabian B. Fuchs , Martin Engelcke , Michael A. Osborne , Ingmar Posner