• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • On Algorithmic Statistics for Space-Bounded Algorithms
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
May 18, 2026
The 'Second Shift' Is Not Why Women Avoid News
Women are more likely than men to avoid political and economic news, but the reasons for this behaviour are linked less to structural inequality or family-related stress than to personal attitudes and the emotional perception of news content. This conclusion was reached by HSE researchers after analysing data from a large-scale survey of more than 10,000 residents across 61 regions of Russia. The study findings have been published in Woman in Russian Society.
May 15, 2026
Preserving Rationality in a Period of Turbulence
The HSE International Laboratory for Logic, Linguistics and Formal Philosophy studies logic and rationality in a transformed world characterised by a diversity of logical systems and rational agents. The laboratory supports and develops academic ties with Russian and international partners. The HSE News Service spoke with the head of the laboratory, Prof. Elena Dragalina-Chernaya, about its work.
May 15, 2026
‘All My Time Is Devoted to My Dissertation
Ilya Venediktov graduated from the Master’s programme at the HSE Tikhonov Moscow Institute of Electronics and Mathematics through the combined Master’s–PhD track and is currently studying at the HSE Doctoral School of Engineering Sciences. At present, he is undertaking a long-term research internship at the University of Science and Technology of China in Hefei, where he is preparing his dissertation. In this interview, he explains how an internship differs from an academic mobility programme, discusses his research topic, and describes the daily life of a Russian doctoral student in China.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

On Algorithmic Statistics for Space-Bounded Algorithms

P. 232–244.
Milovanov A.

Algorithmic statistics studies explanations of observed data that are good in the algorithmic sense: an explanation should be simple i.e. should have small Kolmogorov complexity and capture all the algorithmically discoverable regularities in the data. However this idea can not be used in practice because Kolmogorov complexity is not computable.

In this paper we develop algorithmic statistics using space-bounded Kolmogorov complexity. We prove an analogue of one of the main result of ‘classic’ algorithmic statistics (about the connection between optimality and randomness deficiences). The main tool of our proof is the Nisan-Wigderson generator.

Language: English
DOI
Text on another site
Keywords: Kolmogorov complexityalgorithmic statistics
Publication based on the results of:
Теоретическая информатика (2017)

In book

Computer Science – Theory and Applications: 12th International Computer Science Symposium in Russia (CSR 2017)
Vol. 10304. , Luxemburg: Springer, 2017.
Similar publications
О базовых математических определениях цифровых технологий и искусственного интеллекта
Semenov A., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2025 Т. 527 № S С. 7–12
The paper proposes a system of definitions for the basic concepts of computability theory that underlie the mathematics of the digital world: algorithm, computability, calculus, object complexity, close to modern undertnding. Hierarchies of the finite and the problem of consistency are considered. ...
Added: December 6, 2025
Kolmogorov’s Last Discovery? (Kolmogorov and Algorithmic Statistics)
Semenov A., Shen A., Vereshchagin N., Theory of Probability and its Applications, USA 2024 Vol. 68 No. 4 P. 582–606
The definition of descriptional complexity of finite objects suggested by Kolmogorov and other authors in the mid-1960s is now well known. In addition, Kolmogorov pointed out some approaches to a more fine-grained classification of finite objects, such as the resource-bounded complexity (1965), structure function (1974), and the notion of $(\alpha,\beta)$-stochasticity (1981). Later it turned out ...
Added: January 16, 2025
On information content in certain objects
Vereshchagin N., / Series arXiv "math". 2024.
The fine approach to measure information dependence is based on the total conditional complexity CT(y|x), which is defined as the minimal length of a total program that outputs y on the input x. It is known that the total conditional complexity can be much larger than than the plain conditional complexity. Such strings x, y ...
Added: August 19, 2024
Universal almost optimal compression and Slepian-Wolf coding in probabilistic polynomial time
Bauwens B. F., Zimand M., Journal of the ACM 2023 Vol. 70 No. 2 Article 9
In a lossless compression system with target lengths, a compressor 𝒞 maps an integer m and a binary string x to an m-bit code p, and if m is sufficiently large, a decompressor 𝒟 reconstructs x from p. We call a pair (m,x) achievable for (𝒞,𝒟) if this reconstruction is successful. We introduce the notion ...
Added: March 22, 2023
Inequalities for space-bounded Kolmogorov complexity
Bauwens B. F., Gács P., Romashchenko A. et al., Computability 2022 Vol. 11 No. 3-4 P. 165–185
Finding all linear inequalities for entropies remains an important open question in information theory. For a long time the only known inequalities for entropies of tuples of random variables were Shannon (submodularity) inequalities. Only in 1998 Zhang and Yeung 1998 found the first inequality that cannot be represented as a convex combination of Shannon inequalities, and ...
Added: December 23, 2022
Information disclosure in the framework of kolmogorov complexity
Vereshchagin N., Theoretical Computer Science 2023 Vol. 940 P. 108–122
We consider the network consisting of three nodes 1, 2, 3 connected by two open channels 1 → 2 and 1 → 3. The information present in the node 1 consists of four strings x , y , z , w. The nodes 2, 3 know x , w and need to know y , z, respectively. ...
Added: December 19, 2022
Predictions and Algorithmic Statistics for Infinite Sequences
Milovanov A., , in: Computer Science – Theory and Applications: 16th International Computer Science Symposium in Russia, CSR 2021, Sochi, Russia, June 28–July 2, 2021, Proceedings.: Springer, 2021. Ch. 17 P. 283–295.
We combine Solomonoff’s approach to universal prediction with algorithmic statistics and suggest to use the computable measure that provides the best “explanation” for the observed data (in the sense of algorithmic statistics) for prediction. In this way we keep the expected sum of squares of prediction errors bounded (as it was for the Solomonoff’s predictor) ...
Added: August 11, 2021
The normalized algorithmic information distance can not be approximated
Bauwens B. F., Blinnikov I., , in: Computer Science – Theory and Applications 15th International Computer Science Symposium in Russia, CSR 2020, Yekaterinburg, Russia, June 29 – July 3, 2020, ProceedingsVol. 12159.: Springer, 2020. P. 130–141.
It is known that the normalized algorithmic information distance is not computable and not semicomputable. We show that for all 𝜀<1/2, there exist no semicomputable functions that differ from N by at most 𝜀. Moreover, for any computable function f such that |lim𝑡𝑓(𝑥,𝑦,𝑡)−N(𝑥,𝑦)|≤𝜀 and for all n, there exist strings x, y of length n such that ...
Added: February 5, 2021
Information Distance Revisited
Bauwens B. F., , in: 37th International Symposium on Theoretical Aspects of Computer Science (STACS 2020)Vol. 154: Leibniz International Proceedings in Informatics (LIPIcs).: Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik, 2020. P. 46:1–46:14.
Added: March 20, 2020
Descriptive complexity of computable sequences revisited
Vereshchagin N., Theoretical Computer Science 2020 Vol. 809 P. 531–537
The purpose of this paper is   to answer two questions left open in [B. Durand, A. Shen, and N. Vereshchagin, Descriptive Complexity of Computable Sequences, Theoretical Computer Science 171 (2001), pp. 47--58].   Namely, we consider   the following two   complexities of an infinite computable 0-1-sequence $\alpha$:   $C^{0'}(\alpha )$, defined as ...
Added: January 17, 2020
Algorithmic Statistics: Forty Years Later.
Shen A., Vereshchagin N., , in: Computability and Complexity.: Berlin: Springer, 2017. P. 669–737.
Algorithmic statistics has two different (and almost orthogonal) motivations. From the philosophical point of view, it tries to formalize how the statistics works and why some statistical models are better than others. After this notion of a "good model" is introduced, a natural question arises: it is possible that for some piece of data there ...
Added: October 26, 2018
On Algorithmic Statistics for Space-bounded Algorithms
Milovanov A., Theory of Computing Systems 2019 Vol. 63 No. 4 P. 833–848
Algorithmic statistics looks for models of observed data that are good in the following sense: a model is simple (i.e., has small Kolmogorov complexity) and captures all the algorithmically discoverable regularities in the data. However, this idea can not be used in practice as is because Kolmogorov complexity is not computable. In this paper we ...
Added: October 17, 2018
Plain stopping time and conditional complexities revisited
Posobin G. I., Shen A., Andreev M., , in: 43rd International Symposium on Mathematical Foundations of Computer Science (MFCS 2018)Vol. 117.: Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik, 2018. P. 1–24.
In this paper we analyze the notion of "stopping time complexity", informally defined as the amount of information needed to specify when to stop while reading an infinite sequence. This notion was introduced by Vovk and Pavlovic (2016). It turns out that plain stopping time complexity of a binary string x could be equivalently defined as (a) ...
Added: October 11, 2018
A Structural Lemma for Deterministic Context-Free Languages
Rubtsov A. A., , in: Developments in Language Theory 22nd International Conference, DLT 2018, Tokyo, Japan, September 10-14, 2018, Proceedings.: Cham: Springer, 2018. P. 553–565.
We present a new structural lemma for deterministic con- text free languages. From the first sight, it looks like a pumping lemma, because it is also based on iteration properties, but it has significant distinctions that makes it much easier to apply. The structural lemma is a combinatorial analogue of KC-DCF-Lemma (based on Kolmogorov complexity), ...
Added: September 12, 2018
Algorithmic Statistics and Prediction for Polynomial Time-Bounded Algorithms
Milovanov A., , in: Sailing Routes in the World of Computation.: Springer, 2018. P. 287–296.
Algorithmic statistics studies explanations of observed data that are good in the algorithmic sense: an explanation should be simple i.e. should have small Kolmogorov complexity and capture all the algorithmically discoverable regularities in the data. However this idea can not be used in practice as is because Kolmogorov complexity is not computable. In recent years resource-bounded ...
Added: September 4, 2018
Kolmogorov complexity and algorithmic randomness
Shen A., Uspensky V. A., Vereshchagin N., American Mathematical Society, 2017.
Added: October 12, 2017
Stochasticity in Algorithmic Statistics for Polynomial Time
Vereshchagin N., Milovanov A., , in: 32nd Computational Complexity Conference.: Вадерн: Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl Publishing, 2017. P. 1–18.
A fundamental notion in Algorithmic Statisticsis that of a stochastic object, i.e., an object having a simple plausible explanation. Informally, a probability distribution is a plausible explanation for x if it looks likely that x was drawn at random with respect to that distribution. In this paper, we suggest three definitions of a plausible statistical ...
Added: October 12, 2017
Short lists with short programs in short time
Vereshchagin N., Bauwens B. F., Makhlin A. et al., Computational Complexity 2018 Vol. 27 No. 1 P. 31–61
Given a machine $U$, a $c$-short program for $x$ is a string $p$ such that $U(p)=x$ and the length of $p$ is bounded by $c$ + (the length of a shortest program for $x$). We show that for any universal  machine, it is possible to compute  in polynomial time  on input $x$ a  list of ...
Added: April 22, 2017
Stochasticity in Algorithmic Statistics for Polynomial Time
Vereshchagin N., Milovanov A., / Series Technical report "Electronic Colloquium on Computational Complexity". 2017. No. TR17-043.
Added: March 7, 2017
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit