English
Related papers

Related papers: Optimality of Universal Bayesian Sequence Predicti…

200 papers

Consider universal data compression: the length $l(x^n)$ of sequence $x^n\in A^n$ with finite alphabet $A$ and length $n$ satisfies Kraft's inequality over $A^n$, and $-\frac{1}{n}\log \frac{P^n(x^n)}{Q^n(x^n)}$ almost surely converges to…

Information Theory · Computer Science 2014-05-26 Joe Suzuki

Assume one observes independent categorical variables or, equivalently, one observes the corresponding multinomial variables. Estimating the distribution of the observed sequence amounts to estimating the expectation of the multinomial…

Statistics Theory · Mathematics 2009-06-15 C. Durot , E. Lebarbier , A. -S. Tocquet

We revisit the classical problem of universal prediction of stochastic sequences with a finite time horizon $T$ known to the learner. The question we investigate is whether it is possible to derive vanishing regret bounds that hold with…

Machine Learning · Computer Science 2026-02-19 Matthias Frey , Jonathan H. Manton , Jingge Zhu

The predictability of a sequence is defined as the asymptotic performance of the best performing predictor in a given class. The value of the predictability of a sequence will in general depend on the choice of this predictor class. The…

Statistics Theory · Mathematics 2009-04-15 Finn Macleod , Alexei Pokrovskii , Dima Rachinskii

In this paper, we derive optimality results for greedy Bayesian-network search algorithms that perform single-edge modifications at each step and use asymptotically consistent scoring criteria. Our results extend those of Meek (1997) and…

Artificial Intelligence · Computer Science 2013-01-07 David Maxwell Chickering , Christopher Meek

The forward prediction problem for a 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 the process…

Probability · Mathematics 2008-06-19 Gusztav Morvai

This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonoff's universal prior M, the latter being an excellent…

Information Theory · Computer Science 2007-07-16 Marcus Hutter

Let $(B_t)_{0\leq t\leq T}$ be either a Bernoulli random walk or a Brownian motion with drift, and let $M_t:=\max\{B_s: 0\leq s\leq t\}$, $0\leq t\leq T$. This paper solves the general optimal prediction problem \sup_{0\leq\tau\leq…

Probability · Mathematics 2011-02-09 Pieter C. Allaart

This paper reviews the growing field of Bayesian prediction. Bayes point and interval prediction are defined and exemplified and situated in statistical prediction more generally. Then, four general approaches to Bayes prediction are…

Methodology · Statistics 2025-02-06 Bertrand Clarke , Yuling Yao

We address the problem of nonparametric estimation of characteristics for stationary and ergodic time series. We consider finite-alphabet time series and real-valued ones and the following four problems: i) estimation of the (limiting)…

Information Theory · Computer Science 2007-11-01 Boris Ryabko

The problem is sequence prediction in the following setting. A sequence $x_1,...,x_n,...$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\mu$. After observing each outcome, it is required…

Artificial Intelligence · Computer Science 2012-03-20 Daniil Ryabko

This paper presents a method to calculate the exact average block error probability of some random code ensembles under maximum-likelihood decoding. The proposed method is applicable to various channels and ensembles. The focus is on both…

Information Theory · Computer Science 2022-03-01 Ralf R. Müller

We show how universal codes can be used for solving some of the most important statistical problems for time series. By definition, a universal code (or a universal lossless data compressor) can compress any sequence generated by a…

Information Theory · Computer Science 2008-09-09 Boris Ryabko

This article describes a robust algorithm to estimate a conditional probability density f(t|x) as a non-parametric smooth regression function. It is based on a neural network and the Bayesian interpretation of the network output as a…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Michael Feindt

We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive optimisation algorithms such as AdaGrad and Adam. We demonstrate…

Machine Learning · Statistics 2020-07-21 Samuel Kessler , Arnold Salas , Vincent W. C. Tan , Stefan Zohren , Stephen Roberts

Stochastic optimal control with unknown randomness distributions has been studied for a long time, encompassing robust control, distributionally robust control, and adaptive control. We propose a new episodic Bayesian approach that…

Optimization and Control · Mathematics 2025-06-02 Alexander Shapiro , Enlu Zhou , Yifan Lin , Yuhao Wang

We initiate a systematic study of utilizing predictions to improve over approximation guarantees of classic algorithms, without increasing the running time. We propose a systematic method for a wide class of optimization problems that ask…

Data Structures and Algorithms · Computer Science 2024-11-26 Antonios Antoniadis , Marek Eliáš , Adam Polak , Moritz Venzin

The prediction of a binary sequence is a classic example of online machine learning. We like to call it the 'stock prediction problem,' viewing the sequence as the price history of a stock that goes up or down one unit at each time step. In…

Optimization and Control · Mathematics 2020-07-28 Nadejda Drenska , Robert V. Kohn

For exponentially distributed lifetimes, we consider the prediction of future order statistics based on having observed the first $m$ order statistics. We focus on the previously less explored aspects of predicting: (i) an arbitrary pair of…

Statistics Theory · Mathematics 2024-03-12 Akbar Asgharzadeh , Éric Marchand , Ali Saadati Nik

The machine learning literature contains several constructions for prediction intervals that are intuitively reasonable but ultimately ad-hoc in that they do not come with provable performance guarantees. We present methods from the…

Machine Learning · Statistics 2020-02-25 Danijel Kivaranovic , Kory D. Johnson , Hannes Leeb
‹ Prev 1 3 4 5 6 7 10 Next ›