中文
相关论文

相关论文: On Universal Prediction and Bayesian Confirmation

200 篇论文

We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true distribution m by the algorithmic complexity of m. Here we…

机器学习 · 计算机科学 2007-07-16 Alexey Chernov , Marcus Hutter

There are three principle paradigms of statistical inference: (i) Bayesian, (ii) information-based and (iii) frequentist inference. We describe an objective prior (the weighting or $w$-prior) which unifies objective Bayes and…

机器学习 · 统计学 2015-06-26 Colin H. LaMont , Paul A. Wiggins

We investigate the use of randomly generated data for the sake of pre-training a model. We justify this approach theoretically from the perspective of algorithmic complexity, building on recent research that shows that sequence models can…

机器学习 · 计算机科学 2025-06-26 Peter Bloem

We introduce a graphical framework for Bayesian inference that is sufficiently general to accommodate not just the standard case but also recent proposals for a theory of quantum Bayesian inference wherein one considers density operators…

量子物理 · 物理学 2012-08-23 Bob Coecke , Robert W. Spekkens

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…

机器学习 · 统计学 2023-03-16 Adrian N. Bishop , Edwin V. Bonilla

We present a general framework for Bayesian inference of causal effects that delivers provably robust inferences founded on design-based randomization of treatments. The framework involves fixing the observed potential outcomes and forming…

统计方法学 · 统计学 2025-11-04 Easton Huch , Fred Feinberg , Walter Dempsey

Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a…

机器学习 · 计算机科学 2007-07-16 Marcus Hutter , Andrej Muchnik

The progress of machine learning over the past decade is undeniable. In retrospect, it is both remarkable and unsettling that this progress was achievable with little to no rigorous theory to guide experimentation. Despite this fact,…

机器学习 · 统计学 2025-05-23 Hong Jun Jeon , Benjamin Van Roy

We present a universal framework for constructing confidence sets based on sequential likelihood mixing. Building upon classical results from sequential analysis, we provide a unifying perspective on several recent lines of work, and…

机器学习 · 统计学 2025-02-21 Johannes Kirschner , Andreas Krause , Michele Meziu , Mojmir Mutny

Ray Solomonoff invented the notion of universal induction featuring an aptly termed "universal" prior probability function over all possible computable environments. The essential property of this prior was its ability to dominate all other…

信息论 · 计算机科学 2011-11-17 Ian Wood , Peter Sunehag , Marcus Hutter

We consider the Bayesian analysis of a few complex, high-dimensional models and show that intuitive priors, which are not tailored to the fine details of the model and the estimated parameters, produce estimators which perform poorly in…

统计理论 · 数学 2015-02-02 Y. Ritov , P. J. Bickel , A. C. Gamst , B. J. K. Kleijn

Bayesian learning is built on an assumption that the model space contains a true reflection of the data generating mechanism. This assumption is problematic, particularly in complex data environments. Here we present a Bayesian…

机器学习 · 统计学 2018-11-05 S. P. Lyddon , S. G. Walker , C. C. Holmes

In this paper we propose a general framework to analyze prediction in time series models and show how a wide class of popular time series models satisfies this framework. We postulate a set of high-level assumptions, and formally verify…

计量经济学 · 经济学 2019-02-06 Eric Beutner , Alexander Heinemann , Stephan Smeekes

The problem of sequential probability forecasting is considered in the most general setting: a model set C is given, and it is required to predict as well as possible if any of the measures (environments) in C is chosen to generate the…

机器学习 · 计算机科学 2019-10-25 Daniil Ryabko

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…

人工智能 · 计算机科学 2020-09-01 Zhenyu A. Liao , Charupriya Sharma , James Cussens , Peter van Beek

We develop an efficient Bayesian sequential inference framework for factor analysis models observed via various data types, such as continuous, binary and ordinal data. In the continuous data case, where it is possible to marginalise over…

统计方法学 · 统计学 2022-01-28 Konstantinos Vamvourellis , Konstantinos Kalogeropoulos , Irini Moustaki

We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor $M$ from the true distribution $mu$ by the algorithmic complexity of $mu$. Here…

机器学习 · 计算机科学 2007-07-16 A. Chernov , M. Hutter , J. Schmidhuber

We theoretically justify the recent empirical finding of [Teh et al., 2025] that a transformer pretrained on synthetically generated data achieves strong performance on empirical Bayes (EB) problems. We take an indirect approach to this…

机器学习 · 统计学 2026-02-18 Nick Cannella , Anzo Teh , Yanjun Han , Yury Polyanskiy

Various optimality properties of universal sequence predictors based on Bayes-mixtures in general, and Solomonoff's prediction scheme in particular, will be studied. The probability of observing $x_t$ at time $t$, given past observations…

机器学习 · 计算机科学 2007-05-23 Marcus Hutter

Ensembles of neural networks (NNs) have long been used to estimate predictive uncertainty; a small number of NNs are trained from different initialisations and sometimes on differing versions of the dataset. The variance of the ensemble's…

机器学习 · 计算机科学 2018-11-30 Tim Pearce , Mohamed Zaki , Andy Neely