中文
相关论文

相关论文: General Loss Bounds for Universal Sequence Predict…

200 篇论文

Estimation of parameters that obey specific constraints is crucial in statistics and machine learning; for example, when parameters are required to satisfy boundedness, monotonicity, or linear inequalities. Traditional approaches impose…

统计方法学 · 统计学 2026-04-03 Lachlan Astfalck , Deborshee Sen , Sayan Patra , Edward Cripps , David Dunson

The problem is that of sequential probability forecasting for finite-valued time series. The data is generated by an unknown probability distribution over the space of all one-way infinite sequences. It is known that this measure belongs to…

统计理论 · 数学 2016-11-02 Daniil Ryabko

When people learn mathematical patterns or sequences, they are able to identify the concepts (or rules) underlying those patterns. Having learned the underlying concepts, humans are also able to generalize those concepts to other numbers,…

机器学习 · 计算机科学 2020-01-14 Mohith Damarapati , Inavamsi B. Enaganti , Alfred Ajay Aureate Rajakumar

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…

机器学习 · 计算机科学 2014-01-24 N. Denizcan Vanli , Suleyman S. Kozat

Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves…

机器学习 · 计算机科学 2007-07-13 Marcus Hutter

In Generalised Bayesian Inference (GBI), the learning rate and hyperparameters of the loss must be estimated. These inference-hyperparameters can't be estimated jointly with the other parameters, from the data, by giving them a prior.…

统计方法学 · 统计学 2026-05-18 Jeong Eun Lee , Sitong Liu , Geoff K. Nicholls

We investigate the data distribution valuation problem, which aims to quantify the values of data distributions from their samples. This is a recently proposed problem that is related to but different from classical data valuation and can…

机器学习 · 计算机科学 2026-04-08 Cuong N. Nguyen , Cuong V. Nguyen

Standard Bayesian analyses can be difficult to perform when the full likelihood, and consequently the full posterior distribution, is too complex and difficult to specify or if robustness with respect to data or to model misspecifications…

统计方法学 · 统计学 2019-01-08 Federica Giummolè , Valentina Mameli , Erlis Ruli , Laura Ventura

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…

信息论 · 计算机科学 2007-08-20 Marcus Hutter , Andrej Muchnik

In this paper, we obtain generic bounds on the variances of estimation and prediction errors in time series analysis via an information-theoretic approach. It is seen in general that the error bounds are determined by the conditional…

信息论 · 计算机科学 2021-05-12 Song Fang , Mikael Skoglund , Karl Henrik Johansson , Hideaki Ishii , Quanyan Zhu

Given a sequence $X=(X_1,X_2,\ldots)$ of random observations, a Bayesian forecaster aims to predict $X_{n+1}$ based on $(X_1,\ldots,X_n)$ for each $n\ge 0$. To this end, in principle, she only needs to select a collection…

统计方法学 · 统计学 2023-01-30 Patrizia Berti , Emanuela Dreassi , Fabrizio Leisen , Pietro Rigo , Luca Pratelli

The Bayesian statistical paradigm uses the language of probability to express uncertainty about the phenomena that generate observed data. Probability distributions thus characterize Bayesian analysis, with the rules of probability used to…

统计计算 · 统计学 2020-12-08 Gael M. Martin , David T. Frazier , Christian P. Robert

Universal outlier hypothesis testing refers to a hypothesis testing problem where one observes a large number of length-$n$ sequences -- the majority of which are distributed according to the typical distribution $\pi$ and a small number…

信息论 · 计算机科学 2026-01-05 Bernhard C. Geiger , Tobias Koch , Josipa Mihaljević , Maximilian Toller

Solomonoff unified Occam's razor and Epicurus' principle of multiple explanations to one elegant, formal, universal theory of inductive inference, which initiated the field of algorithmic information theory. His central result is that the…

机器学习 · 计算机科学 2008-06-26 Marcus Hutter

This chapter provides a overview of Bayesian inference, mostly emphasising that it is a universal method for summarising uncertainty and making estimates and predictions using probability statements conditional on observed data and an…

统计方法学 · 统计学 2010-02-11 Christian P. Robert , Jean-Michel Marin , Judith Rousseau

Is it a good idea to use the frequency of events in the past, as a guide to their frequency in the future (as we all do anyway)? In this paper the question is attacked from the perspective of universal prediction of individual sequences. It…

信息论 · 计算机科学 2013-01-29 Yuval Lomnitz , Meir Feder

The statistical inverse problem of estimating the probability distribution of an infinite-dimensional unknown given its noisy indirect observation is studied in the Bayesian framework. In practice, one often considers only…

统计理论 · 数学 2017-11-21 Sari Lasanen

In two recent articles we have examined a generalization of the binomial distribution associated with a sequence of positive numbers, involving asymmetric expressions of probabilities that break the symmetry {\it win-loss}. We present in…

数学物理 · 物理学 2015-06-17 H. Bergeron , E. M. F. Curado , J. P. Gazeau , Ligia M. C. S. Rodrigues

The forecasting problem for a stationary and ergodic binary time series $\{X_n\}_{n=0}^{\infty}$ is to estimate the probability that $X_{n+1}=1$ based on the observations $X_i$, $0\le i\le n$ without prior knowledge of the distribution of…

概率论 · 数学 2008-06-19 Gusztav Morvai , Benjamin Weiss

We consider a model of selective prediction, where the prediction algorithm is given a data sequence in an online fashion and asked to predict a pre-specified statistic of the upcoming data points. The algorithm is allowed to choose when to…

机器学习 · 计算机科学 2019-05-30 Mingda Qiao , Gregory Valiant