no code implementations • 3 Sep 2023 • Vladimir Vovk
In this paper I discuss both syntax and semantics of subjective probability.
no code implementations • 2 Nov 2021 • Vladimir Vovk, Ilia Nouretdinov, Alex Gammerman
We continue study of conformal testing in binary model situations.
no code implementations • 4 Jul 2021 • Vladimir Vovk, Ivan Petej, Alex Gammerman
This note proposes a way of making probability forecasting rules less sensitive to changes in data distribution, concentrating on the simple case of binary classification.
no code implementations • 18 May 2021 • Vladimir Vovk
This note proposes a procedure for enhancing the quality of probabilistic prediction algorithms via betting against their predictions.
no code implementations • 5 Apr 2021 • Vladimir Vovk
Conformal testing is a way of testing the IID assumption based on conformal prediction.
no code implementations • 20 Feb 2021 • Vladimir Vovk, Ivan Petej, Ilia Nouretdinov, Ernst Ahlberg, Lars Carlsson, Alex Gammerman
We argue for supplementing the process of training a prediction algorithm by setting up a scheme for detecting the moment when the distribution of the data changes and the algorithm needs to be retrained.
no code implementations • 28 Dec 2020 • Vladimir Vovk
This note continues study of exchangeability martingales, i. e., processes that are martingales under any exchangeable distribution for the observations.
no code implementations • 14 May 2020 • Nicolo Colombo, Vladimir Vovk
Efficiency criteria for conformal prediction, such as \emph{observed fuzziness} (i. e., the sum of p-values associated with false labels), are commonly used to \emph{evaluate} the performance of given conformal predictors.
no code implementations • 16 Jan 2020 • Vladimir Vovk
This note discusses a simple modification of cross-conformal prediction inspired by recent work on e-values.
no code implementations • 3 Nov 2019 • Vladimir Vovk, Ivan Petej, Ilia Nouretdinov, Valery Manokhin, Alex Gammerman
Conformal predictive systems are a recent modification of conformal predictors that output, in regression problems, probability distributions for labels of test observations rather than set predictions.
no code implementations • 21 Jun 2019 • Vladimir Vovk
This paper reviews known methods of testing the two hypotheses concentrating on the online mode of testing, when the observations arrive sequentially.
no code implementations • 18 Feb 2019 • Vladimir Vovk, Ivan Petej, Paolo Toccaceli, Alex Gammerman
Most existing examples of full conformal predictive systems, split-conformal predictive systems, and cross-conformal predictive systems impose severe restrictions on the adaptation of predictive distributions to the test object at hand.
1 code implementation • 5 Feb 2018 • Glenn Shafer, Vladimir Vovk
April 25, 2003, marked the 100th anniversary of the birth of Andrei Nikolaevich Kolmogorov, the twentieth century's foremost contributor to the mathematical and philosophical foundations of probability.
History and Overview Probability 60-03 (Primary) 01A60, 60A05 (Secondary)
no code implementations • 24 Oct 2017 • Vladimir Vovk, Ilia Nouretdinov, Valery Manokhin, Alex Gammerman
This paper reviews the checkered history of predictive distributions in statistics and discusses two developments, one from recent literature and the other new.
no code implementations • 6 Aug 2017 • Vladimir Vovk
This paper describes simple universally consistent procedures of probability forecasting that satisfy a natural property of small-sample validity, under the assumption that the observations are produced independently in the IID fashion.
no code implementations • 11 Jun 2017 • Denis Volkhonskiy, Ilia Nouretdinov, Alexander Gammerman, Vladimir Vovk, Evgeny Burnaev
We consider the problem of quickest change-point detection in data streams.
no code implementations • 14 Mar 2016 • Vladimir Vovk, Ilia Nouretdinov, Valentina Fedorova, Ivan Petej, Alex Gammerman
We study optimal conformity measures for various criteria of efficiency of classification in an idealised setting.
no code implementations • 14 Mar 2016 • Vladimir Vovk, Dusko Pavlovic
We construct universal prediction systems in the spirit of Popper's falsifiability and Kolmogorov complexity and randomness.
1 code implementation • NeurIPS 2015 • Vladimir Vovk, Ivan Petej, Valentina Fedorova
This paper studies theoretically and empirically a method of turning machine-learning algorithms into probabilistic predictors that automatically enjoys a property of validity (perfect calibration) and is computationally efficient.
no code implementations • 22 Feb 2015 • Vladimir Vovk
The standard loss functions used in the literature on probabilistic prediction are the log loss function, the Brier loss function, and the spherical loss function; however, any computable proper loss function can be used for comparison of prediction algorithms.
no code implementations • 9 Aug 2014 • Alexey Chernov, Vladimir Vovk
In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts.
no code implementations • 21 Jun 2014 • Vladimir Vovk, Ivan Petej, Valentina Fedorova
This paper proposes a new method of probabilistic prediction, which is based on conformal prediction.
no code implementations • 8 Apr 2014 • Evgeny Burnaev, Vladimir Vovk
Conformal prediction is a method of producing prediction sets that can be applied on top of a wide range of prediction algorithms.
no code implementations • 16 Jan 2014 • Harris Papadopoulos, Vladimir Vovk, Alex Gammerman
A comparison of the predictive regions produced by our measures with those of the typical regression measure suggests that a major improvement in terms of predictive region tightness is achieved by the new measures.
1 code implementation • 20 Dec 2012 • Vladimir Vovk, Ruodu Wang
An old result by R\"uschendorf and, independently, Meng implies that the p-values can be combined by scaling up their arithmetic mean by a factor of 2 (and no smaller factor is sufficient in general).
Statistics Theory Statistics Theory 62G10, 62F03
1 code implementation • 31 Oct 2012 • Vladimir Vovk, Ivan Petej
This paper continues study, both theoretical and empirical, of the method of Venn prediction, concentrating on binary prediction problems.
no code implementations • 2 Nov 2006 • Alexander Gammerman, Vladimir Vovk
Recent advances in machine learning make it possible to design efficient prediction algorithms for data sets with huge numbers of parameters.