arXiv subjects

Egor Gladin

Publications and source records attributed to Egor Gladin.

10 recordsLinked to original sources

arXiv2026

Mathematical methods of reinforcement learning

Reinforcement learning (RL) is increasingly grounded in tools from probability, optimization, and operator theory. This survey organizes the mathematical structures that underpin the design and analysis of modern algorithms in RL. We begin from Markov decision processes (MDPs) and the Bellman operators, emphasizing contraction mappings, monotonicity, and fixed-point theory that yield convergence guarantees and rates for value and policy iteration, and temporal-difference schemes. We then develop the optimization perspective: stochastic approximation and martingale methods, convex duality and the role of regularization linking mirror/proximal methods. Function approximation is treated through linear and non-linear settings, covering stabilization, error decomposition, and sample-complexity via concentration inequalities for dependent data and mixing processes. We further cover off-policy evaluation/learning, constrained RL and constrained MDPs (CMDPs). Throughout we unify algorithmic templates under common operator and variational lenses, highlighting both finite-sample bounds and asymptotic results. Our presentation is intended to provide a unified mathematical entry point for researchers in probability, optimization, and statistics interested in reinforcement learning.

math.OC↗

arXiv2025

Improved Stochastic Optimization of LogSumExp

The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In practice, when the number of exponential terms inside the logarithm is large or infinite, optimization becomes challenging since computing the gradient requires differentiating every term. We propose a novel convexity- and smoothness-preserving approximation to LogSumExp that can be efficiently optimized using stochastic gradient methods. This approximation is rooted in a sound modification of the KL divergence in the dual, resulting in a new $f$-divergence called the Safe KL divergence. Our experiments and theoretical analysis of the LogSumExp-based stochastic optimization, arising in DRO and continuous OT, demonstrate the advantages of our approach over existing baselines.

math.OC↗

arXiv2024

Interaction-Force Transport Gradient Flows

This paper presents a new gradient flow dissipation geometry over non-negative and probability measures. This is motivated by a principled construction that combines the unbalanced optimal transport and interaction forces modeled by reproducing kernels. Using a precise connection between the Hellinger geometry and the maximum mean discrepancy (MMD), we propose the interaction-force transport (IFT) gradient flows and its spherical variant via an infimal convolution of the Wasserstein and spherical MMD tensors. We then develop a particle-based optimization algorithm based on the JKO-splitting scheme of the mass-preserving spherical IFT gradient flows. Finally, we provide both theoretical global exponential convergence guarantees and improved empirical simulation results for applying the IFT gradient flows to the sampling task of MMD-minimization. Furthermore, we prove that the spherical IFT gradient flow enjoys the best of both worlds by providing the global exponential convergence guarantee for both the MMD and KL energy.

cs.LG↗

arXiv2023

Accuracy Certificates for Convex Minimization with Inexact Oracle

Accuracy certificates for convex minimization problems allow for online verification of the accuracy of approximate solutions and provide a theoretically valid online stopping criterion. When solving the Lagrange dual problem, accuracy certificates produce a simple way to recover an approximate primal solution and estimate its accuracy. In this paper, we generalize accuracy certificates for the setting of inexact first-order oracle, including the setting of primal and Lagrange dual pair of problems. We further propose an explicit way to construct accuracy certificates for a large class of cutting plane methods based on polytopes. As a by-product, we show that the considered cutting plane methods can be efficiently used with a noisy oracle even thought they were originally designed to be equipped with an exact oracle. Finally, we illustrate the work of the proposed certificates in the numerical experiments highlighting that our certificates provide a tight upper bound on the objective residual.

math.OC↗

arXiv2022

Solving strongly convex-concave composite saddle point problems with a small dimension of one of the variables

The article is devoted to the development of algorithmic methods ensuring efficient complexity bounds for strongly convex-concave saddle point problems in the case when one of the groups of variables is high-dimensional, and the other is relatively low-dimensional (up to a hundred). The proposed technique is based on reducing problems of this type to a problem of minimizing a convex (maximizing a concave) functional in one of the variables, for which it is possible to find an approximate gradient at an arbitrary point with the required accuracy using an auxiliary optimization subproblem with another variable. In this case, the ellipsoid method is used for low-dimensional problems (if necessary, with an inexact $δ$-subgradient), and accelerated gradient methods are used for high-dimensional problems. For the case of a very small dimension of one of the groups of variables (up to 5), an approach based on a new version of the multidimensional analog of the Yu. E. Nesterov's method on the square (multidimensional dichotomy) is proposed with the possibility of using inexact values of the gradient of the objective functional.

math.OC↗

arXiv2022

Algorithm for Constrained Markov Decision Process with Linear Convergence

The problem of constrained Markov decision process is considered. An agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its costs (the number of constraints is relatively small). A new dual approach is proposed with the integration of two ingredients: entropy regularized policy optimizer and Vaidya's dual optimizer, both of which are critical to achieve faster convergence. The finite-time error bound of the proposed approach is provided. Despite the challenge of the nonconcave objective subject to nonconcave constraints, the proposed approach is shown to converge (with linear rate) to the global optimum. The complexity expressed in terms of the optimality gap and the constraint violation significantly improves upon the existing primal-dual approaches.

math.OC↗

arXiv2022

Vaidya's method for convex stochastic optimization in small dimension

This paper considers a general problem of convex stochastic optimization in a relatively low-dimensional space (e.g., 100 variables). It is known that for deterministic convex optimization problems of small dimensions, the fastest convergence is achieved by the center of gravity type methods (e.g., Vaidya's cutting plane method). For stochastic optimization problems, the question of whether Vaidya's method can be used comes down to the question of how it accumulates inaccuracy in the subgradient. The recent result of the authors states that the errors do not accumulate on iterations of Vaidya's method, which allows proposing its analog for stochastic optimization problems. The primary technique is to replace the subgradient in Vaidya's method with its probabilistic counterpart (the arithmetic mean of the stochastic subgradients). The present paper implements the described plan, which ultimately leads to an effective (if parallel computations for batching are possible) method for solving convex stochastic optimization problems in relatively low-dimensional spaces.

math.OC↗

arXiv2021

Solving smooth min-min and min-max problems by mixed oracle algorithms

In this paper, we consider two types of problems that have some similarity in their structure, namely, min-min problems and min-max saddle-point problems. Our approach is based on considering the outer minimization problem as a minimization problem with inexact oracle. This inexact oracle is calculated via inexact solution of the inner problem, which is either minimization or a maximization problem. Our main assumptions are that the problem is smooth and the available oracle is mixed: it is only possible to evaluate the gradient w.r.t. the outer block of variables which corresponds to the outer minimization problem, whereas for the inner problem only zeroth-order oracle is available. To solve the inner problem we use accelerated gradient-free method with zeroth-order oracle. To solve the outer problem we use either inexact variant of Vaydya's cutting-plane method or a variant of accelerated gradient method. As a result, we propose a framework that leads to non-asymptotic complexity bounds for both min-min and min-max problems. Moreover, we estimate separately the number of first- and zeroth-order oracle calls which are sufficient to reach any desired accuracy.

math.OC↗

arXiv2021

On solving convex min-min problems with smoothness and strong convexity in one variable group and small dimension of the other

This paper is devoted to some approaches for convex min-min problems with smoothness and strong convexity in only one of the two variable groups. It is shown that the proposed approaches, based on Vaidya's cutting plane method and Nesterov's fast gradient method, achieve the linear convergence. The outer minimization problem is solved using Vaidya's cutting plane method, and the inner problem (smooth and strongly convex) is solved using the fast gradient method. Due to the importance of machine learning applications, we also consider the case when the objective function is a sum of a large number of functions. In this case, the variance-reduced accelerated gradient algorithm is used instead of Nesterov's fast gradient method. The numerical experiments' results illustrate the advantages of the proposed procedures for logistic regression with the prior on one of the parameter groups.

math.OC↗

arXiv2020

Ellipsoid method for convex stochastic optimization in small dimension

The article considers minimization of the expectation of convex function. Problems of this type often arise in machine learning and a number of other applications. In practice, stochastic gradient descent (SGD) and similar procedures are often used to solve such problems. We propose to use the ellipsoid method with minibatching, which converges linearly and hence requires significantly less iterations than SGD. This is verified by our experiments, which are publicly available. The algorithm does not require neither smoothness nor strong convexity of target function to achieve linear convergence. We prove that the method arrives at approximate solution with given probability when using minibatches of size proportional to the desired precision to the power -2. This enables efficient parallel execution of the algorithm, whereas possibilities for batch parallelization of SGD are rather limited. Despite fast convergence, ellipsoid method can result in a greater total number of calls to oracle than SGD, which works decently with small batches. Complexity is quadratic in dimension of the problem, hence the method is suitable for relatively small dimensionalities.

math.OC↗