Nikita Doikov

According to our database, Nikita Doikov authored at least 24 papers between 2018 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Gradient-Normalized Smoothness for Optimization with Approximate Hessians.

Andrei Semenov, Martin Jaggi, Nikita Doikov

CoRR, June, 2025

First and Zeroth-Order Implementations of the Regularized Newton Method with Lazy Approximated Hessians.

Nikita Doikov, Geovani Nunes Grapiglia

J. Sci. Comput., April, 2025

Cubic regularized subspace Newton for non-convex optimization.

Jim Zhao, Nikita Doikov, Aurélien Lucchi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

Improving Stochastic Cubic Newton with Momentum.

El Mahdi Chayti, Nikita Doikov, Martin Jaggi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Super-Universal Regularized Newton Method.

Nikita Doikov, Konstantin Mishchenko, Yurii E. Nesterov

SIAM J. Optim., March, 2024

Gradient regularization of Newton method with Bregman distances.

Nikita Doikov, Yurii E. Nesterov

Math. Program., March, 2024

Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods.

El Mahdi Chayti, Martin Jaggi, Nikita Doikov

Trans. Mach. Learn. Res., 2024

On Convergence of Incremental Gradient for Non-convex Smooth Functions.

Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions.

Nikita Doikov, Sebastian U. Stich, Martin Jaggi

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Affine-invariant contracting-point methods for Convex Optimization.

Nikita Doikov, Yurii E. Nesterov

Math. Program., March, 2023

Minimizing Quasi-Self-Concordant Functions by Gradient Regularization of Newton Method.

Nikita Doikov

CoRR, 2023

Shuffle SGD is Always Better than SGD: Improved Analysis of SGD with Arbitrary Data Orders.

Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi

CoRR, 2023

Polynomial Preconditioning for Gradient Methods.

Nikita Doikov, Anton Rodomanov

Proceedings of the International Conference on Machine Learning, 2023

Second-Order Optimization with Lazy Hessians.

Nikita Doikov, El Mahdi Chayti, Martin Jaggi

Proceedings of the International Conference on Machine Learning, 2023

Linearization Algorithms for Fully Composite Optimization.

Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

High-Order Optimization Methods for Fully Composite Problems.

Nikita Doikov, Yurii E. Nesterov

SIAM J. Optim., September, 2022

Local convergence of tensor methods.

Nikita Doikov, Yurii E. Nesterov

Math. Program., 2022

2021

New second-order and tensor methods in convex optimization.

Nikita Doikov

PhD thesis, 2021

Minimizing Uniformly Convex Functions by Cubic Regularization of Newton Method.

Nikita Doikov, Yurii E. Nesterov

J. Optim. Theory Appl., 2021

2020

Contracting Proximal Methods for Smooth Convex Optimization.

Nikita Doikov, Yurii E. Nesterov

SIAM J. Optim., 2020

Convex optimization based on global lower second-order models.

Nikita Doikov, Yurii E. Nesterov

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Stochastic Subspace Cubic Newton Method.

Filip Hanzely, Nikita Doikov, Yurii E. Nesterov, Peter Richtárik

Proceedings of the 37th International Conference on Machine Learning, 2020

Inexact Tensor Methods with Dynamic Accuracies.

Nikita Doikov, Yurii E. Nesterov

Proceedings of the 37th International Conference on Machine Learning, 2020

2018

Randomized Block Cubic Newton Method.

Nikita Doikov, Peter Richtárik

Proceedings of the 35th International Conference on Machine Learning, 2018