Alexey Naumov
- Директор института по фундаментальным исследованиям:Faculty of Computer Science / AI and Digital Science Institute
- Laboratory Head:Faculty of Computer Science / AI and Digital Science Institute / International Laboratory of Stochastic Algorithms and High-Dimensional Inference
- Associate Professor:Faculty of Computer Science / Department of Complex System Modelling Technologies
- Programme Academic Supervisor:Math of Machine Learning
- Member of the HSE Academic Council
- Alexey Naumov has been at HSE University since 2016.
Education and Degrees
- 2022
Doctor of Sciences*
HSE University - 2013
Candidate of Sciences* (PhD)
Lomonosov Moscow State University - 2013
PhD
Bielefeld University - 2010
Degree
Lomonosov Moscow State University
According to the International Standard Classification of Education (ISCED) 2011, Candidate of Sciences belongs to ISCED level 8 - "doctoral or equivalent", together with PhD, DPhil, D.Lit, D.Sc, LL.D, Doctorate or similar. Candidate of Sciences allows its holders to reach the level of the Associate Professor.
A post-doctoral degree called Doctor of Sciences is given to reflect second advanced research qualifications or higher doctorates in ISCED 2011.
Continuing education / Professional retraining / Internships / Study abroad experience
Chinese University of Hong Kong, Department of Statistics, Hong Kong, Sep. 2015 -- Dec. 2015.
Bielefeld University, Faculty of Mathematics, Jan. 2013 -- Nov. 2013.
Awards
Yandex Scientific Award (2022)
First award on 39-th competition of young scientists of Moscow State University, 2015.
Courses (2023/2024)
- High Dimensional Probability and Statistics (Mago-Lego; 3, 4 module)Eng
- High Dimensional Probability and Statistics (Master’s programme; Faculty of Computer Science; 1 year, 3, 4 module)Eng
- Mathematical Foundations of Reinforcement learning (Mago-Lego; 2 module)Eng
- Mathematical Foundations of Reinforcement learning (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
- Mentor's Seminar "Math of Machine Learning " (Master’s programme; Faculty of Computer Science; 1 year, 1-4 module)Eng
- Mentor's Seminar "Math of Machine Learning " (Master’s programme; Faculty of Computer Science; 2 year, 1-3 module)Eng
- Past Courses
Courses (2022/2023)
- High Dimensional Probability and Statistics (Master’s programme; Faculty of Computer Science; 1 year, 3, 4 module)Eng
- Markov Chains (Master’s programme; Faculty of Computer Science; 1 year, 2, 3 module)Eng
- Mathematical Foundations of Reinforcement learning (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
- Mathematical Statistics (advanced course) (Bachelor’s programme; Faculty of Computer Science; 2 year, 3, 4 module)Rus
- Random Matrix Theory (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Eng
- Research Seminar (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
Courses (2021/2022)
- Mathematical Foundations of Reinforcement learning (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
- Modern Methods of Data Analysis: Stochastic Calculus (Master’s programme; Faculty of Computer Science; 1 year, 1, 2 module)Eng
- Random Matrix Theory (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Eng
- Research Seminar (Master’s programme; Faculty of Computer Science; 2 year, 1, 2 module)Eng
Courses (2020/2021)
- Modern Methods of Data Analysis: Stochastic Calculus (Master’s programme; Faculty of Computer Science; 1 year, 1, 2 module)Eng
- Random Matrix Theory (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Eng
- Research Seminar (Master’s programme; Faculty of Computer Science; 2 year, 1, 2 module)Eng
Courses (2019/2020)
- Modern Methods of Data Analysis: Stochastic Calculus (Master’s programme; Faculty of Computer Science; 1 year, 1, 2 module)Eng
- Random Matrix Theory (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Eng
- Research Seminar (Master’s programme; Faculty of Computer Science; 2 year, 1-3 module)Eng
Courses (2018/2019)
- Calculus 2 (Bachelor’s programme; Faculty of Computer Science; 2 year, 1-4 module)Rus
- Modern Methods of Data Analysis: Stochastic Calculus (Master’s programme; Faculty of Computer Science; 1 year, 1, 2 module)Eng
Grants
RSF grant № 19-71-30020, "Applications of probabilistic artificial neural generative models to development of digital twin technology for non-linear stochastic systems", 2019 - 2022 (HSE University)
RSF grant № 18-11-00132, "Analysis of high dimensional random objects with applications to large-scale data processing", 2018-2020 (HSE University)
Presidents of Russian Federation Grant for young scientists № 4596.2016.1, "Local laws for random matrices and universality of local spectral statistics", 2016-2017 (Lomonosov MSU, Skoltech)
RFBR grant 16-31-00005 ”Spectral analysis of large dimensional random matrices”, 2016–2017 (Lomonosov MSU, Skoltech)
Publications39
- Article Durmus A., Moulines E., Naumov A., Samsonov S. Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation // Mathematics of Operations Research. 2024. Vol. -. No. -. Article -.
- Article Durmus A., Moulines E., Naumov A., Samsonov S. Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains // Journal of Theoretical Probability. 2024. Vol. -. No. - doi
- Article Puchkin N., Samsonov S., Belomestny D., Moulines E., Naumov A. Rates of convergence for density estimation with generative adversarial networks // Journal of Machine Learning Research. 2024. Vol. 25. No. 29. P. 1-47.
- Article Belomestny D., Goldman A., Naumov A., Samsonov S. Theoretical guarantees for neural control variates in MCMC // Mathematics and Computers in Simulation. 2024. Vol. 220. P. 382-405. doi
- Chapter Tiapkin D., Belomestny D., Calandriello D., Moulines E., Munos R., Naumov A., Perrault P., Tang Y., Valko M., Menard P. Fast Rates for Maximum Entropy Exploration, in: Proceedings of the 40th International Conference on Machine Learning: Volume 202: International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii, USA Vol. 202: International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii, USA. PMLR, 2023. P. 34161-34221.
- Chapter Beznosikov A., Samsonov S., Sheshukova M., Gasnikov A., Naumov A., Moulines E. First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities, in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Curran Associates, Inc., 2023. P. 44820-44835.
- Chapter Tiapkin D., Belomestny D., Calandriello D., Moulines E., Munos R., Naumov A., Perrault P., Valko M., Menard P. Model-free Posterior Sampling via Learning Rate Randomization, in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Curran Associates, Inc., 2023. P. 73719-73774.
- Preprint Durmus A., Moulines E., Naumov A., Samsonov S., Sheshukova M. Rosenthal-type inequalities for linear statistics of Markov chains / Cornell University. Series arXiv "math". 2023. doi
- Article Tiapkin D., Belomestny D., Naumov A., Valko M., Menard P. Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms // Working papers by Cornell University. Series math "arxiv.org". 2023. Article 2304.03056.
- Article Belomestny D., Naumov A., Puchkin N., Samsonov S. Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations // Neural Networks. 2023. Vol. 161. P. 242-253. doi
- Chapter Tiapkin D., Belomestny D., Moulines E., Naumov A., Samsonov S., Tang Y., Valko M., Menard P. From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses, in: Proceedings of the 39th International Conference on Machine Learning Vol. 162. PMLR, 2022. P. 21380-21431.
- Chapter Samsonov S., Lagutin E., Gabrie M., Durmus A., Naumov A., Moulines E. Local-Global MCMC kernels: the best of both worlds, in: Thirty-Sixth Conference on Neural Information Processing Systems : NeurIPS 2022. Curran Associates, Inc., 2022. P. 5178-5193.
- Chapter Tiapkin D., Belomestny D., Calandriello D., Éric Moulines, Munos R., Naumov A., Rowland M., Valko M., Menard P. Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees, in: Thirty-Sixth Conference on Neural Information Processing Systems : NeurIPS 2022. Curran Associates, Inc., 2022. P. 10737-10751.
- Article Масютин А. А., Савченко А. В., Наумов А. А., Самсонов С. В., Тяпкин Д. Н., Беломестный Д. В., Морозова Д. С., Бадьина Д. А. О разработке прикладных решений на основе искусственного интеллекта для обеспечения технологической безопасности // Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика). 2022. Т. 508. № 106. С. 23-27. doi
- Chapter Durmus A., Moulines E., Naumov A., Samsonov S., Wai H. On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning, in: Proceedings of Machine Learning Research Vol. 134: Conference on Learning Theory. PMLR, 2021. P. 1711-1752.
- Chapter Durmus A., Moulines E., Naumov A., Samsonov S., Scaman K., Wai H. Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize, in: Advances in Neural Information Processing Systems 34 (NeurIPS 2021). Curran Associates, Inc., 2021. P. 30063-30074.
- Chapter Bobkov S., Naumov A., Ulyanov V. V. Two–Sided Bounds for PDF’s Maximum of a Sum of Weighted Chi-square Variables, in: Recent Developments in Stochastic Methods and Applications: ICSM-5, Moscow, Russia, November 23–27, 2020, Selected Contributions Vol. 371. Springer, 2021. doi P. 178-189. doi
- Article Belomestny D., Levin I., Moulines E., Naumov A., Samsonov S., Zorina V. UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms // Working papers by Cornell University. Series math "arxiv.org". 2021. Article 2105.02135.
- Article Belomestny D., Iosipoi L., Moulines E., Naumov A., Samsonov S. Variance reduction for dependent sequences with applications to Stochastic Gradient MCMC // SIAM-ASA Journal on Uncertainty Quantification. 2021. Vol. 9. No. 2. P. 507-535. doi
- Chapter Kaledin M., Moulines E., Naumov A., Tadic V., Wai H. Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise, in: Proceedings of Machine Learning Research Vol. 125: Proceedings of Thirty Third Conference on Learning Theory. , 2020. P. 2144-2203.
- Article Naumov A., Tikhomirov A., Гётце Ф. Local Semicircle Law Under Fourth Moment Condition // Journal of Theoretical Probability. 2020. Vol. 33. No. 3. P. 1327-1362. doi
- Article Гётце Ф., Naumov A., Tikhomirov A. Local laws for non-Hermitian random matrices and their products // Random Matrices-Theory and Applications. 2020. Vol. 9. No. 4. P. 2150004. doi
- Article Götze F., Naumov A., Tikhomirov A. Moment Inequalities for Linear and Nonlinear Statistics // Theory of Probability and Its Applications. 2020. Vol. 65. No. 1. P. 1-16. doi
- Chapter Bobkov S., Naumov A., Ulyanov V. V. Two-sided bounds for PDF's maximum of a sum of weighted chi-square variables, in: Сборник материалов V-й Международной конференции по стохастическим методам: The 5th International Conference on Stochastic Methods (ICSM5). 23-27 November 2020, Russia, Moscow.. M. : RUDN, 2020. P. 39-42.
- Article Belomestny D., Moulines E., Iosipoi L., Naumov A., Samsonov S. Variance reduction for Markov chains with application to MCMC // Statistics and Computing. 2020. No. 30. P. 973-997. doi
- Article Naumov A., Spokoiny V., Ulyanov V. V. Bootstrap confidence sets for spectral projectors of sample covariance // Probability Theory and Related Fields. 2019. Vol. 174. No. 3-4. P. 1091-1132. doi
- Article Goetze F., Naumov A., Spokoiny V., Ulyanov V. V. Large ball probability, Gaussian comparison and anti-concentration // Bernoulli: a journal of mathematical statistics and probability. 2019. Vol. 25. No. 4(A). P. 2538-2563. doi
- Article Naumov A., Tikhomirov A., Гётце Ф. On Optimal Bounds in the Local Semicircle Law under Four Moment Condition / Пер. с рус. // Doklady Mathematics. 2019. Vol. 99. No. 1. P. 40-43. doi
- Article Naumov A., Spokoiny V., Ulyanov V. V. Confidence Sets for Spectral Projectors of Covariance Matrices / Пер. с рус. // Doklady Mathematics. 2018. Vol. 98. No. 2. P. 511-514. doi
- Article Naumov A., Tikhomirov A., Goetze F. Local Semicircle Law under Moment Conditions: The Stieltjes Transform, Rigidity, and Delocalization // Theory of Probability and Its Applications. 2018. Vol. 62. No. 1. P. 58-83. doi
- Article Naumov A., Spokoiny V., Ulyanov V. V., Tavyrikov Y. Nonasymptotic Estimates for the Closeness of Gaussian Measures on Balls, / Пер. с рус. // Doklady Mathematics. 2018. Vol. 98. No. 2. P. 490-493. doi
- Article Goetze F., Naumov A.A., Tikhomirov A. On the local semicircular law for Wigner ensembles // Bernoulli: a journal of mathematical statistics and probability. 2018. Vol. 24. No. 3. P. 2358-2400. doi
- Article Ulyanov V. V., Goetze F., A. Naumov. Asymptotic analysis of symmetric functions // Journal of Theoretical Probability. 2017. Vol. 30. No. 3. P. 876-897. doi
- Article Goetze F., Naumov A.A., Tikhomirov A. Distribution of linear statistics of singular values of the product of random matrices // Bernoulli: a journal of mathematical statistics and probability. 2017. Vol. 23. No. 4B. P. 3067-3113. doi
- Article Goetze F., Naumov A., Tikhomirov A. Local Laws for Non-Hermitian Random Matrices // Doklady Mathematics. 2017. Vol. 96. No. 3. P. 558-560. doi
- Article Naumov A., Гётце Ф., Tikhomirov A. Local Semicircle Law under Weak Moment Conditions / Пер. с рус. // Doklady Mathematics. 2016. Vol. 93. No. 3. P. 248-250. doi
- Article Naumov A., Tikhomirov A., Гётце Ф. LIMIT THEOREMS FOR TWO CLASSES OF RANDOM MATRICES WITH DEPENDENT ENTRIES / Пер. с рус. // Theory Probability and its Applications. 2015. Vol. 59. No. 1. P. 23-39. doi
- Article Naumov A., Tikhomirov A., Гётце Ф. ON A GENERALIZATION OF THE ELLIPTIC LAW FOR RANDOM MATRICES // Acta Physica Polonica, Series B.. 2015. Vol. 46. No. 9. P. 1737-1745. doi
- Article Goetze F., Naumov A.A., Tikhomirov A. On minimal singular values of random matrices with correlated entries // Random Matrices-Theory and Applications. 2015. Vol. 4. No. 2 doi
‘The Goal of the Spring into ML School Is to Unite Young Scientists Engaged in Mathematics of AI’
The AI and Digital Science Institute at the HSE Faculty of Computer Science and Innopolis University organised a week-long programme for students, doctoral students, and young scientists on the application of mathematics in machine learning and artificial intelligence. Fifty participants of Spring into ML attended 24 lectures on machine learning, took part in specific pitch sessions, and completed two mini-courses on diffusion models—a developing area of AI for data generation.
‘Every Article on NeurIPS Is Considered a Significant Result’
Staff members of the HSE Faculty of Computer Science will present 12 of their works at the 37th Conference and Workshop on Neural Information Processing Systems (NeurIPS), one of the most significant events in the field of artificial intelligence and machine learning. This year it will be held on December 10–16 in New Orleans (USA).
HSE University Hosts Fall into ML 2023 Conference on Machine Learning
Over three days, more than 300 conference participants attended workshops, seminars, sections and a poster session. During panel discussions, experts deliberated on the regulation of artificial intelligence (AI) technologies and considered collaborative initiatives between academic institutions and industry to advance AI development through megaprojects.
Fall into ML 2023: HSE University’s Faculty of Computer Science Organises Conference on Machine Learning
On October 26–28, HSE University’s Institute of Artificial Intelligence and Digital Sciences at the Faculty of Computer Science will hold a conference titled Fall into ML 2023 withsupport from the HSE University AI Research Centre . The event is dedicated to promising directions of fundamental AI development.
Faculty of Computer Science and AI Centre Welcome Applications to Binary Super Resolution Challenge
From July 18 to October 15, 2023, the HSE University Faculty of Computer Science and AI Centre invite those interested to take part in the online Binary Super Resolution Challenge (BSRC-2023). The top 50 teams will receive prizes, and the top three will receive cash prizes.
Days of Computer Science Held as HSE University
Every spring, HSE University’s Faculty of Computer Science, which this year turns nine years old, traditionally opens its doors and invites everyone to a festival. This time, more than 20 events with over 2,000 registered participants were held between April 8th and 16th as part of the Days of Computer Science.
HSE University’s Joint Master’s Programme with Skoltech Named Best Educational Initiative at Data Fusion Awards 2023
VTB, CNews, and Skolkovo have announced the winners of the Data Fusion Awards 2023, a nationwide cross-industry award in the sphere of big data technology. The awards recognise the top projects in the public sector, business, and education. The English-taught Master’s programme Math of Machine Learning, implemented jointly by HSE University’s Faculty of Computer Science and the Skolkovo Institute of Science and Technology, was named the educational initiative of the year. Second place in this category was awarded to the Graduate School of Business’s Master’s programme Business Analytics and Big Data Systems.
HSE Researchers Contribute to Artificial Intelligence Journey Conference
The AI Journey international conference is a major platform for sharing cutting-edge innovations in artificial intelligence and machine learning. In late November 2022, AIJ was once again hosted by Sber. The conference was attended by HSE researchers from the Faculty of Computer Science and the Centre for Artificial Intelligence.
Three HSE Researchers Receive Ilya Segalovich Award
Three researchers of the HSE Faculty of Computer Science are among the winners of the 2022 Ilya Segalovich Award: Research Professor Dmitry Vetrov, Associate Professor Alexey Naumov and doctoral student Sergey Samsonov. The award, established by Yandex in 2019, is aimed at supporting young researchers and the scientific community in the field of IT in Russia, Belarus and Kazakhstan.
Fall into ML: Autumn School and Conference on Machine Learning Held at HSE University
On November 1st-3rd, 2022 the International Laboratory of Stochastic Algorithms and High-Dimensional Inference of the HSE Faculty of Computer Science and the Laboratory of Methods for Big Data Analysis with the support of HSE AI Centre and the Russian Science Foundation organized the first autumn school and conference on artificial intelligence ‘Fall into ML’. The new format of the event included a school for students and young researchers.
17 Articles by Researchers of HSE Faculty of Computer Science Accepted at NeurIPS
In 2022, 17 articles by the researchers of HSE Faculty of Computer Science were accepted at the NeurIPS (Conference and Workshop on Neural Information Processing Systems), one of the world’s most prestigious events in the field of machine learning and artificial intelligence. The 36th conference will be held in a hybrid format from November 28th to December 9th in New Orleans (USA).
HSE Faculty of Computer Science and Skoltech Hold Math of Machine Learning Olympiad 2022
HSE's Faculty of Computer Science and the Skolkovo Institute of Science and Technology have held the Mathematics of Machine Learning Olympiad for the fifth time. The participants competed for prizes and the opportunity to matriculate at two universities without exams by enrolling in the HSE and Skoltech joint master's programme in Math of Machine Learning.
SAMPLE Conference Takes Place
On October 26-30, Statistics, Artificial Intelligence, Machine Learning, Probability, Learning Theory Event (SAMPLE) conference took place in Gelendzhik, Russia.
Faculty Submits Ten Papers to NeurIPS 2021
35th Conference on Neural Information Processing Systems (NeurIPS 2021) is one of the world's largest conferences on machine learning and neural networks. It takes place on December 6-14, 2021.
HSE University Becomes the First Russian University to Confer a Doctoral Degree in Computer Science
Upon successfully defending his dissertation before HSE Dissertation Council in Computer Science, Pavel Dvurechensky became the first Doctor of Computer Science in Russia. This was possible thanks to the fact that, starting in 2018, HSE University received the right to award its own academic degrees.
Faculty of Computer Science and Skoltech Host Third Statistical Learning Theory Olympiad
HSE University’s Faculty of Computer Science and Skoltech have organised Statistical Learning Theory Olympiad for the third time. The Olympiad’s main award is admission to the HSE University and Skoltech joint master’s programme.
"I Am Impressed by the Sirius Atmosphere"
Sirius held a conference school arranged by the Talent and Success Foundation, Yandex, and the International Laboratory of Stochastic Algorithms and High-Dimensional Inference of HSE University.
First Cohort Graduates from Master’s Programme in Statistical Learning Theory
The Master's Programme in Statistical Learning Theory was launched in 2017. It is run jointly with the Skolkovo Institute of Science and Technology (Skoltech). The programme trains future scientists to effectively carry out fundamental research and work on new challenging problems in statistical learning theory, one of the most promising fields of science. Yury Kemaev and Maxim Kaledin, from the first cohort of programme graduates, sat down with HSE News Service to talk about their studies and plans for the future.
First Cohort Graduates from Master’s Programme in Statistical Learning Theory
The Master's Programme ‘Statistical Learning Theory’ was launched in 2017, and is run jointly with the Skolkovo Institute of Science and Technology(Skoltech).
HDI Lab staff attend International Vilnius Conference on Probability Theory and Mathematical Statistics 2018
12th International Vilnius Conference on Probability Theory and Mathematical Statistics and 2018 IMS Annual Meeting on Probability and Statistics took place in Vilnius (Lithuania) on July 2-6. This is one of the world's leading conferences in the field of modern probability theory and mathematical statistics, which is held every four years since 1973. This year over 200 works were presented at the event and 500 participants from all over the globe attended it.
Structural Learning Seminar Summer Meeting
On 19 July at 11 am an extraordinary meeting of Structural Learning Seminar was held on the Faculty of Computer Science.
Laboratory Researchers Received Russian Science Foundation Grant
Team of researchers of the HSE International Laboratory of Stochastic Algorithms and High-Dimensional Inference was announced as a winner of the Russian Science Foundation Grant Competition to support fundamental and exploratory scientific research conducted by individual scientific groups and was awarded three-year grant for implementation of the project "Analysis of high dimensional random objects with applications to large scale data processing" (RSF №18-11-00132).
HSE Lends Its Support to the Very First Conference in ‘New Frontiers in High-Dimensional Probability and Statistics’
On February 23 and 24, the Institute for Information Transmission Problems of the Russian Academy of Sciences hosted the first international mini-conference entitled ‘New frontiers in high-dimensional probability and statistics’. The event was attended by Russian and international researchers in the field of statistical methods of analysis of multidimensional data and modern stochastic algorithms. The conference was hosted by HSE, the Institute for Information Transmission Problems of the RAS and Skoltech. Organisers included HSE Faculty of Computer Science staff, Vladimir Spokoiny, Alexey Naumov, Denis Belomestny and Quentin Paris.
‘Our Programme Aims to Make a Research Breakthrough at the Intersection of Mathematics and Computer Science’
In 2017, the HSE Faculty of Computer Science and Skoltech are opening admissions to the Master’s programme inStatistical Learning Theory, which will become the successor to theMathematical Methods of Optimization and Stochastics programme.Vladimir Spokoiny, the programme’s academic supervisor and professor of mathematics at Humboldt University in Berlin, told us about the research part of the new programme and the opportunities it offers to both Master’s students and undergraduate students alike.