collaborators

10 papers

math.OC2026

Primal Acceleration of Newton's Method

Nikita Doikov

We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. The algorithm uses only primal variables and performs just one…

cs.LG2026

On Optimization Complexity of Second-Order Certified Unlearning

Nikita Doikov, Anastasia Koloskova

We study machine unlearning: the removal of memorized training data from a trained model. Specifically, we investigate the algorithmic complexity of certified unlearning from an op…

cs.LG2026

PACER: Acyclic Causal Discovery from Large-Scale Interventional Data

Ramon Viñas Torné, Sílvia Fà bregas Salazar, Soyon Park +4

Inferring the structure of directed acyclic graphs (DAGs) from data is a central challenge in causal discovery, particularly in modern high-dimensional settings where large-scale i…

math.OC2025

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

El Mahdi Chayti, Nikita Doikov, Martin Jaggi

We study stochastic Cubic Newton methods for solving general possibly non-convex minimization problems. We propose a new framework, which we call the helper framework, that provide…

math.OC2025

Universal Reduced-Operator Method and High-Order Global Curvature Bounds

Nikita Doikov, Yurii Nesterov

In this paper, we develop a new concept of Global Curvature Bound (GCB) for an arbitrary nonlinear operator between abstract metric spaces. We use this notion to characterize the g…

math.OC2025

On the Complexity of Lower-Order Implementations of Higher-Order Methods

Nikita Doikov, Geovani Nunes Grapiglia

In this work, we propose a method for minimizing non-convex functions with Lipschitz continuous th-order derivatives, starting from . The method, however, only require…