activity
20242026
collaborators

6 papers

cs.LG2026

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods

Andrey Veprikov, Arman Bolatov, Aleksandr Bogdanov +4

Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utiliza…

math.OC2025

Loss-Transformation Invariance in the Damped Newton Method

Alexander Shestakov, Sushil Bohara, Samuel Horváth +2

The Newton method is a powerful optimization algorithm, valued for its rapid local convergence and elegant geometric properties. However, its theoretical guarantees are usually lim…

math.OC2025

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees

Artem Agafonov, Vladislav Ryspayev, Samuel Horváth +3

Quasi-Newton methods are widely used for solving convex optimization problems due to their ease of implementation, practical efficiency, and strong local convergence guarantees. Ho…

math.OC2025

Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge

Farshed Abdukhakimov, Cuong Anh Pham, Samuel Horváth +2

The Polyak stepsize for Gradient Descent is known for its fast convergence but requires prior knowledge of the optimal functional value, which is often unavailable in practice. In…

math.OC2024

Newton Method Revisited: Global Convergence Rates up to for Stepsize Schedules and Linesearch Procedures

Slavomír Hanzely, Farshed Abdukhakimov, Martin Takáč

This paper investigates the global convergence of stepsized Newton methods for convex functions with Hölder continuous Hessians or third derivatives. We propose several simple ste…

cs.LG2024

DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning

Klea Ziu, Slavomír Hanzely, Loka Li +3

Learning the structure of Directed Acyclic Graphs (DAGs) presents a significant challenge due to the vast combinatorial search space of possible graphs, which scales exponentially…