?
Low-Variance Black-Box Gradient Estimates for the Plackett-Luce Distribution
P. 10126–10135.
Springer Publishing Company, 2025.
The three-volume set LNCS 14476-14478 constitutes the post conference proceedings of the 4th International Conference on Numerical Computations: Theory and Algorithms, NUMTA 2023, held in Pizzo Calabro, Italy, during June 14–20, 2023.
The 45 full papers presented in this book together with 60 short papers were carefully reviewed and selected from 170 submissions.
The papers focus on ...
Added: November 23, 2025
Кочкаров А. А., Yatskin D., Рахманов О. А., Известия ЮФУ. Технические науки 2016 № 2 С. 158–168
The problem of limited space monitoring is formulated. The connection between the monitoring space and the detection of objects in this space sets up. After introducing some assumptions we conclude the necessity of solving the covering set (connected space) problem. The presence of obstacles in the monitoring area is the characteristic feature of the problem. ...
Added: March 7, 2025
Kornilov N., Gasnikov A., Dvurechensky P. et al., Computational Management Science 2023 Article 37
We present two easy-to-implement gradient-free/zeroth-order methods to optimize a stochastic non-smooth function accessible only via a black-box. The methods are built upon efficient first-order methods in the heavy-tailed case, i.e., when the gradi- ent noise has infinite variance but bounded (1 + 𝜅)-th moment for some 𝜅 ∈ (0, 1]. The first algorithm is based ...
Added: February 7, 2025
Kodaneva N., Lando S., Journal of Geometry and Physics 2025 Vol. 210 Article 105421
Weight systems are functions on chord diagrams satisfying so-called Vassiliev’s 4-term relations. They are closely related to finite type knot invariants, see [31 Certain weight systems can be derived from graph invariants, see a recent account in [19]. Another main source of weight systems are Lie algebras, the construction due to D. Bar-Natan [3] and ...
Added: January 23, 2025
Gladin E., Alkousa M., Gasnikov A., Automation and Remote Control 2021 Vol. 82 P. 1679–1691
The article deals with some approaches to solving convex problems of the min-min type with smoothness and strong convexity in only one of the two groups of variables. It is shown that the proposed approaches based on Vaidya’s method, the fast gradient method, and the accelerated gradient method with variance reduction have linear convergence. It ...
Added: November 29, 2024
Gladin E., Gasnikov A., Ermakova E., Mathematical notes 2022 Vol. 112 No. 1 P. 183–190
The paper deals with a general problem of convex stochastic optimization in a space of small dimension (for example, 100 variables). It is known that for deterministic problems of convex optimization in small dimensions, the methods of centers of gravity type (for example, Vaidya’s method) provide the best convergence. For stochastic optimization problems, the question ...
Added: November 29, 2024
Gladin E., Зайнуллина К. Э., Компьютерные исследования и моделирование 2021 Т. 13 № 6 С. 1137–1147
The article considers minimization of the expectation of convex function. Problems of this type often arise in machine learning and a variety of other applications. In practice, stochastic gradient descent (SGD) and similar procedures are usually used to solve such problems. We propose to use the ellipsoid method with mini-batching, which converges linearly and can ...
Added: November 29, 2024
Gladin E., Borodich E., Computer Research and Modeling 2022 Vol. 14 No. 2 P. 257–275
The paper is devoted to convex-concave saddle point problems where the objective is a sum of a large number of functions. Such problems attract considerable attention of the mathematical community due to the variety of applications in machine learning, including adversarial learning, adversarial attacks and robust reinforcement learning, to name a few. The individual functions ...
Added: November 29, 2024
Brosse N., Durmus A., Meyn S. et al., Computational Mathematics and Mathematical Physics 2024 Vol. 64 No. 4 P. 693–738
A new method is introduced for the construction of control variates to reduce the variance of additive functionals of Markov Chain Monte Carlo (MCMC) samplers. These control variates are obtained by minimizing the asymptotic variance associated with the Langevin diffusion over a family of functions. To motivate our approach, we then show that the asymptotic ...
Added: October 13, 2024
Alashqar B., Gasnikov A., Dvinskikh D. et al., Computational Mathematics and Mathematical Physics 2023 Vol. 63 P. 1600–1653
This paper studies non-smooth problems of convex stochastic optimization. Using the smoothing technique based on the replacement of the function value at the considered point by the averaged function value over a ball (in l1-norm or l2-norm) of a small radius centered at this point, and then the original problem is reduced to a smooth problem (whose ...
Added: March 27, 2024
Kornilov N., Shamir O., Lobanov A. et al., , in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023).: Curran Associates, Inc., 2023. P. 64083–64102.
Added: March 26, 2024
Schechtman S., Tiapkin D., Muehlebach M. et al., , in: Proceedings of Machine Learning Research: Volume 195: The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, IndiaVol. 195: The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India.: PMLR, 2023. P. 1228–1258.
We consider the problem of minimizing a non-convex function over a smooth manifold M. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM), which only requires computing a projection onto a vector space. ODCGM is infeasible but the iterates are constantly pulled towards the manifold, ensuring the convergence of ODCGM towards M. ...
Added: December 1, 2023
Belomestny D., Kaledin M., Golubev A., /. 2022.
Policy-gradient methods in Reinforcement Learning(RL) are very universal and widely applied in practice but their performance suffers from the high variance of the gradient estimate. Several procedures were proposed to reduce it including actor-critic(AC) and advantage actor-critic(A2C) methods. Recently the approaches have got new perspective due to the introduction of Deep RL: both new control ...
Added: April 14, 2023
Cardoso G., Samsonov S., Thin A. et al., , in: Thirty-Sixth Conference on Neural Information Processing Systems : NeurIPS 2022.: Curran Associates, Inc., 2022. P. 716–729.
Added: February 1, 2023
Морозов Н. Ю., Гришин Е. М., Правдивец Н. А. et al., Управление большими системами: сборник трудов 2022 № 99 С. 135–156
В связи с ростом объема мультимодальных перевозок ОАО «РЖД» требуется более эффективное использование имеющихся ресурсов. В наши дни наиболее востребованной разновидностью международного грузооборота является доставка морским транспортом с последующей перегрузкой на железную дорогу для доставки до пункта назначения на материке. В настоящей статье предлагается комплексная математическая модель, включающая две подзадачи: задачу назначения причалов (BAP) и ...
Added: December 7, 2022
Grishin E., Pravdivets N., Morozov N. et al., IFAC-PapersOnLine 2022 Vol. 55 No. 10 P. 2557–2562
Sea transport holds the first place in the total number of freight shipments of international transportation. Rail transport takes more than 87% of domestic freight traffic and is increasing annually. In particular, Russian Railways deals with scheduling in international multimodal transport. Sea port-railway transshipment points have a key role in the realization of such transportation. ...
Added: December 7, 2022
Smirnov S., Voloshinov V., O.V. Sukhoroslov, , in: Proceedings of the 9th International Conference "Distributed Computing and Grid Technologies in Science and Education" (GRID'2021), Dubna, Russia, July 5-9, 2021.: CEUR Workshop Proceedings, 2021. P. 413–417.
ParaSCIP is rather advanced open-source solver for discrete and global optimization problems. This solver is distinguished by that it can run on distributed memory systems and use up to 80,000 cores, solving open problems from the MIPLIB test libraries. Earlier, using this solver, we confirmed the conjecture on optimal packing of nine congruent circles on ...
Added: October 30, 2022
Beznosikov A., Novitskii V., Gasnikov A., , in: Mathematical Optimization Theory and Operations Research: 20th International Conference, MOTOR 2021, Irkutsk, Russia, July 5–10, 2021, Proceedings.: Cham: Springer, 2021. Ch. 261179 P. 144–158.
In this paper, we analyze gradient-free methods with one-point feedback for stochastic saddle point problems min xmax yφ(x, y). For non-smooth and smooth cases, we present an analysis in a general geometric setup with the arbitrary Bregman divergence. For problems with higher order smoothness, the analysis is carried out only in the Euclidean case. The estimates we have obtained repeat the best currently known estimates of gradient-free ...
Added: October 30, 2022
Dvinskikh D., Tominin V., Tominin I. et al., , in: Mathematical Optimization Theory and Operations Research, 21st International Conference, MOTOR 2022, Petrozavodsk, Russia, July 2–6, 2022, ProceedingsVol. 13367.: Springer, 2022. Ch. 279899 P. 18–33.
Added: October 28, 2022
Tiapkin D., Alexander Gasnikov, , in: International Conference on Artificial Intelligence and Statistics, 28-30 March 2022, A Virtual ConferenceVol. 151: Proceedings of The 25th International Conference on Artificial Intelligence and Statistics.: PMLR, 2022. P. 9723–9740.
We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous functionals. An important detail is the ability to use inexact values of functional constraints and compute the value of dual variables. We analyze ...
Added: October 16, 2022
Schechtman S., Tiapkin D., Moulines E. et al., IFAC-PapersOnLine 2022 Vol. 55 No. 16 P. 236–241
In a recent paper, Muehlebach and Jordan (2021a) proposed a novel algorithm for constrained optimization that uses original ideals from nonsmooth dynamical systems. In this work, we extend Muehlebach and Jordan (2021a) in several important directions: (i) we provide existence and convergence results for continuous-time trajectories under general conditions, and (ii) we provide a convergence ...
Added: October 16, 2022
Tiapkin D., Gasnikov A., Dvurechensky P., Optimization Letters 2022 Vol. 16 No. 7 P. 2145–2175
We consider the population Wasserstein barycenter problem for random probability measures supported on a finite set of points and generated by an online stream of data. This leads to a complicated stochastic optimization problem where the objective is given as an expectation of a function given as a solution to a random optimization problem. We ...
Added: October 16, 2022
М. А. Коврижных, Д. Б. Фомин, Прикладная дискретная математика 2022 № 57 С. 5–21
In this paper, we study a generalized construction of (2m, 2m)-functions using monomial and arbitrary m-bit permutations as constituent elements. We investigate the possibility of constructing bijective vectorial Boolean functions (permutations) with specified cryptographic properties that ensure the resistance of encryption algorithms to linear and differential methods of cryptographic analysis. We propose a heuristic algorithm ...
Added: October 8, 2022