Slavomír Hanzely

14 papers A* 2A 1Journal 10

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods. CoRR Andrey Veprikov, Arman Bolatov, Samuel Horváth, Aleksandr Beznosikov, Martin Takác, Slavomír Hanzely
2025	J	`jnl`	Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees. CoRR Artem Agafonov, Vladislav Ryspayev, Samuel Horváth, Alexander V. Gasnikov, Martin Takác, Slavomír Hanzely
2025	A	`conf`	Sketch-and-Project Meets Newton Method: Global O(1/k AISTATS Slavomír Hanzely
2024	J	`jnl`	ψDAG: Projected Stochastic Approximation Iteration for DAG Structure Learning. CoRR Klea Ziu, Slavomír Hanzely, Loka Li, Kun Zhang, Martin Takác, Dmitry Kamzolov
2023	J	`jnl`	Adaptive Optimization Algorithms for Machine Learning. CoRR Slavomír Hanzely
2023	—	`—`	Adaptive Optimization Algorithms for Machine Learning. Slavomír Hanzely
2023	J	`jnl`	Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes. CoRR Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik
2023	J	`jnl`	Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation. Trans. Mach. Learn. Res. Rustem Islamov, Xun Qian, Slavomír Hanzely, Mher Safaryan, Peter Richtárik
2023	J	`jnl`	Sketch-and-Project Meets Newton Method: Global O(k CoRR Slavomír Hanzely
2022	A*	`conf`	A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate. NeurIPS Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander V. Gasnikov, Peter Richtárik, Martin Takác
2022	J	`jnl`	Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation. CoRR Rustem Islamov, Xun Qian, Slavomír Hanzely, Mher Safaryan, Peter Richtárik
2020	J	`jnl`	Adaptive Learning of the Optimal Mini-Batch Size of SGD. CoRR Motasem Alfarra, Slavomír Hanzely, Alyazeed Albasyoni, Bernard Ghanem, Peter Richtárik
2020	A*	`conf`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. NeurIPS Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik
2020	J	`jnl`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. CoRR Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik