The power of first-order smooth optimization for black-box non-smooth problems
A Gasnikov, A Novitskii, V Novitskii… - arXiv preprint arXiv …, 2022 - arxiv.org
Gradient-free/zeroth-order methods for black-box convex optimization have been
extensively studied in the last decade with the main focus on oracle calls complexity. In this …
extensively studied in the last decade with the main focus on oracle calls complexity. In this …
Randomized gradient-free methods in convex optimization
Consider a convex optimization problem min x∈ Q⊆ Rd f (x)(1) with convex feasible set Q
and convex objective f possessing the zeroth-order (gradient/derivativefree) oracle [83]. The …
and convex objective f possessing the zeroth-order (gradient/derivativefree) oracle [83]. The …
Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm
This work studies minimization problems with zero-order noisy oracle information under the
assumption that the objective function is highly smooth and possibly satisfies additional …
assumption that the objective function is highly smooth and possibly satisfies additional …
Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
Distributed optimization has a rich history. It has demonstrated its effectiveness in many
machine learning applications, etc. In this paper we study a subclass of distributed …
machine learning applications, etc. In this paper we study a subclass of distributed …
Accelerated zero-order sgd method for solving the black box optimization problem under “overparametrization” condition
A Lobanov, A Gasnikov - International Conference on Optimization and …, 2023 - Springer
This paper is devoted to solving a convex stochastic optimization problem in a
overparameterization setup for the case where the original gradient computation is not …
overparameterization setup for the case where the original gradient computation is not …
Zero-order stochastic conditional gradient sliding method for non-smooth convex optimization
A Lobanov, A Anikin, A Gasnikov, A Gornov… - … Optimization Theory and …, 2023 - Springer
The conditional gradient idea proposed by Marguerite Frank and Philip Wolfe in 1956 was
so well received by the community that new algorithms (also called Frank–Wolfe type …
so well received by the community that new algorithms (also called Frank–Wolfe type …
Stochastic adversarial noise in the “black box” optimization problem
A Lobanov - International Conference on Optimization and …, 2023 - Springer
This paper is devoted to the study of the solution of a stochastic convex black box
optimization problem. Where the black box problem means that the gradient-free oracle only …
optimization problem. Where the black box problem means that the gradient-free oracle only …
[PDF][PDF] Gradient free methods for non-smooth convex optimization with heavy tails on convex compact
Optimization problems, in which only the realization of a function or a zeroth-order oracle is
available, have many applications in practice. These are multi-armed bandits, black-box …
available, have many applications in practice. These are multi-armed bandits, black-box …
Gradient-free Federated Learning Methods with l1 and l2-randomization for Non-smooth Convex Stochastic Optimization Problems
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 …
smoothing technique based on the replacement of the function value at the considered point …
Highly smooth zeroth-order methods for solving optimization problems under the PL condition
AV Gasnikov, AV Lobanov, FS Stonyakin - … Mathematics and Mathematical …, 2024 - Springer
In this paper, we study the black box optimization problem under the Polyak–Lojasiewicz
(PL) condition, assuming that the objective function is not just smooth, but has higher …
(PL) condition, assuming that the objective function is not just smooth, but has higher …