Martin Takác

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 40

Top Topics

Conformal Prediction

Vehicle Routing

Stochastic Gradient

Top Venues

Optim. Methods Softw.

Publications

Kun Song, Ruben Solozabal, Hao Li, Martin Takác, Lu Ren, Fakhri Karray
Robustly Train Normalizing Flows via KL Divergence Regularization. AAAI (2024)
Saveliy Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov
Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed. CoRR (2024)
Nazarii Tupitsa, Samuel Horváth, Martin Takác, Eduard Gorbunov
Federated Learning Can Find Friends That Are Beneficial. CoRR (2024)
Petr Ostroukhov, Aigerim Zhumabayeva, Chulu Xiang, Alexander V. Gasnikov, Martin Takác, Dmitry Kamzolov
AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size. CoRR (2024)
Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
Efficient Conformal Prediction under Data Heterogeneity. AISTATS (2024)
Saveliy Chezhegov, Sergey Skorik, Nikolas Khachaturov, Danil Shalagin, Aram Avetisyan, Aleksandr Beznosikov, Martin Takác, Yaroslav Kholodov, Alexander V. Gasnikov
Local Methods with Adaptivity via Scaling. CoRR (2024)
Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takác, Eduard Gorbunov
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad. CoRR (2024)
Aleksandr Beznosikov, Martin Takác
Random-reshuffled SARAH does not need full gradient computations. Optim. Lett. 18 (3) (2024)
Vitali Pirau, Aleksandr Beznosikov, Martin Takác, Vladislav Matyukhin, Alexander V. Gasnikov
Preconditioning meets biased compression for efficient distributed optimization. Comput. Manag. Sci. 21 (1) (2024)
Nicolas Mauricio Cuadrado, Roberto Alejandro Gutiérrez Guillén, Martin Takác
FRESCO: Federated Reinforcement Energy System for Cooperative Optimization. CoRR (2024)
Yunxiang Li, Rui Yuan, Chen Fan, Mark Schmidt, Samuel Horváth, Robert M. Gower, Martin Takác
Enhancing Policy Gradient with the Polyak Step-Size Adaption. CoRR (2024)
Samar Fares, Klea Ziu, Toluwani Aremu, Nikita Durasov, Martin Takác, Pascal Fua, Karthik Nandakumar, Ivan Laptev
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models. CoRR (2024)
Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takác
Stochastic Gradient Methods with Preconditioned Updates. J. Optim. Theory Appl. 201 (2) (2024)
Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
PaDPaF: Partial Disentanglement with Partially-Federated GANs. Trans. Mach. Learn. Res. 2024 (2024)
Artem Agafonov, Dmitry Kamzolov, Alexander V. Gasnikov, Ali Kavis, Kimon Antonakopoulos, Volkan Cevher, Martin Takác
Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness. ICLR (2024)
Yunxiang Li, Nicolas Mauricio Cuadrado, Samuel Horváth, Martin Takác
Generalized Policy Learning for Smart Grids: FL TRPO Approach. CoRR (2024)
Zangir Iklassov, Yali Du, Farkhad Akimov, Martin Takác
Self-Guiding Exploration for Combinatorial Problems. CoRR (2024)
Artem Agafonov, Dmitry Kamzolov, Pavel E. Dvurechensky, Alexander V. Gasnikov, Martin Takác
Inexact tensor methods and their application to stochastic convex optimization. Optim. Methods Softw. 39 (1) (2024)
Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takác, Maxim Panov
Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks. CoRR (2023)
Zangir Iklassov, Ikboljon Sobirov, Ruben Solozabal, Martin Takác
Reinforcement Learning for Solving Stochastic Vehicle Routing Problem. ACML (2023)
Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takác
AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods. Trans. Mach. Learn. Res. 2023 (2023)
Zangir Iklassov, Ikboljon Sobirov, Ruben Solozabal, Martin Takác
Reinforcement Learning for Solving Stochastic Vehicle Routing Problem. CoRR (2023)
Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
Byzantine-Tolerant Methods for Distributed Variational Inequalities. CoRR (2023)
Farshed Abdukhakimov, Chulu Xiang, Dmitry Kamzolov, Martin Takác
Stochastic Gradient Descent with Preconditioned Polyak Step-size. CoRR (2023)
Talal Algumaei, Ruben Solozabal, Réda Alami, Hakim Hacid, Mérouane Debbah, Martin Takác
Regularization of the Policy Updates for Stabilizing Mean Field Games. PAKDD (2) (2023)
Egor Gladin, Maksim Lavrik-Karmazin, Karina Zainullina, Varvara Rudenko, Alexander V. Gasnikov, Martin Takác
Algorithm for Constrained Markov Decision Process with Linear Convergence. AISTATS (2023)
Zangir Iklassov, Dmitrii Medvedev, Ruben Solozabal Ochoa de Retana, Martin Takác
On the Study of Curriculum Learning for Inferring Dispatching Policies on the Job Shop Scheduling. IJCAI (2023)
Asma Ahmed Hashmi, Artem Agafonov, Aigerim Zhumabayeva, Mohammad Yaqub, Martin Takác
In Quest of Ground Truth: Learning Confident Models and Estimating Uncertainty in the Presence of Annotator Noise. CoRR (2023)
Shuang Li, William J. Swartworth, Martin Takác, Deanna Needell, Robert M. Gower
SP2 : A Second Order Stochastic Polyak Method. ICLR (2023)
Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
Byzantine-Tolerant Methods for Distributed Variational Inequalities. NeurIPS (2023)
Nicolas Cuadrado, Roberto Gutierrez, Yongli Zhu, Martin Takác
MAHTM: A Multi-Agent Framework for Hierarchical Transactive Microgrids. CoRR (2023)
Nicolas M. Cuadrado, Roberto Alejandro Gutiérrez Guillén, Martin Takác
FRESCO: Federated Reinforcement Energy System for Cooperative Optimization. Tiny Papers @ ICLR (2023)
Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
Efficient Conformal Prediction under Data Heterogeneity. CoRR (2023)
Zangir Iklassov, Ikboljon Sobirov, Ruben Solozabal, Martin Takác
Reinforcement Learning Approach to Stochastic Vehicle Routing Problem With Correlated Demands. IEEE Access 11 (2023)
Farshed Abdukhakimov, Chulu Xiang, Dmitry Kamzolov, Robert M. Gower, Martin Takác
SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms. CoRR (2023)
Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
Partial Disentanglement with Partially-Federated GANs (PaDPaF). CoRR (2022)
Albert S. Berahas, Majid Jahani, Peter Richtárik, Martin Takác
Quasi-Newton methods for machine learning: forget the past, just sample. Optim. Methods Softw. 37 (5) (2022)
Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander V. Gasnikov, Peter Richtárik, Martin Takác
A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate. NeurIPS (2022)
Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takác, Alexander V. Gasnikov
Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes. EURO J. Comput. Optim. 10 (2022)
Nur Sila Gulgec, Martin Takác, Shamim N. Pakzad
Convolutional Neural Network Approach for Robust Structural Damage Detection and Localization. J. Comput. Civ. Eng. 33 (3) (2019)