PPaperPicks

Martin Takác

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

21 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-7455-2025 ↗Google Scholar ↗Homepage ↗

Venues

ICLR ×5NeurIPS ×5AAAI ×2ACL ×2AISTATS ×2ICML ×2IJCAI ×1MICCAI ×1SDM ×1

Frequent coauthors

Samuel Horváth
×8
Eduard Gorbunov
×5
Alexander V. Gasnikov
×4
Nikita Kotelevskii
×4
Maxim Panov
×4
Artem Agafonov
×4
Aleksandr Beznosikov
×3
Zangir Iklassov
×3
Dmitry Kamzolov
×3
Salem Lahlou
×2
Eric Moulines
×2
Mohammad Yaqub
×2

Papers

  1. Bant: Byzantine Antidote via Trial Function and Trust Scores
    AAAI 2026 ·
    Gleb Molodtsov
    ,
    Daniil Medyakov
    ,
    Sergey Skorik
    ,
    Nikolas Khachaturov
    ,
    Shahane Tigranyan
    ,
    Vladimir Aletov
    ,
    Aram Avetisyan
    , Martin Takác,
    Aleksandr Beznosikov
  2. Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models
    ACL 2026 ·
    Yanda Li
    ,
    Yuhan Liu
    ,
    Zirui Song
    ,
    Yunchao Wei
    , Martin Takác,
    Salem Lahlou
  3. Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
    ICML 2025 ·
    Savelii Chezhegov
    ,
    Yaroslav Klyukin
    ,
    Andrei Semenov
    ,
    Aleksandr Beznosikov
    ,
    Alexander V. Gasnikov
    ,
    Samuel Horváth
    , Martin Takác,
    Eduard Gorbunov
  4. FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
    ICML 2025 ·
    Philip Zmushko
    ,
    Aleksandr Beznosikov
    , Martin Takác,
    Samuel Horváth
  5. From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
    ICLR 2025 ·
    Nikita Kotelevskii
    ,
    Vladimir Kondratyev
    , Martin Takác,
    Eric Moulines
    ,
    Maxim Panov
  6. Learning Confident Classifiers in the Presence of Label Noise
    SDM 2025 ·
    Asma Ahmed Hashmi
    ,
    Aigerim Zhumabayeva
    ,
    Nikita Kotelevskii
    ,
    Artem Agafonov
    ,
    Mohammad Yaqub
    ,
    Maxim Panov
    , Martin Takác
  7. Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
    ACL 2025 ·
    Munachiso Nwadike
    ,
    Zangir Iklassov
    ,
    Toluwani Aremu
    ,
    Tatsuya Hiraoka
    ,
    Benjamin Heinzerling
    ,
    Velibor Bojkovic
    ,
    Hilal AlQuabeh
    , Martin Takác,
    Kentaro Inui
  8. MedNNS: Supernet-Based Medical Task-Adaptive Neural Network Search
    MICCAI 2025 ·
    Lotfi Abdelkrim Mecharbat
    ,
    Ibrahim Almakky
    , Martin Takác,
    Mohammad Yaqub
  9. Methods for Convex (L0, L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity
    ICLR 2025 ·
    Eduard Gorbunov
    ,
    Nazarii Tupitsa
    ,
    Sayantan Choudhury
    ,
    Alen Aliev
    ,
    Peter Richtárik
    ,
    Samuel Horváth
    , Martin Takác
  10. Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
    ICLR 2025 ·
    Yury Demidovich
    ,
    Petr Ostroukhov
    ,
    Grigory Malinovsky
    ,
    Samuel Horváth
    , Martin Takác,
    Peter Richtárik
    ,
    Eduard Gorbunov
  11. OPTAMI: Global Superlinear Convergence of High-order Methods
    ICLR 2025 ·
    Dmitry Kamzolov
    ,
    Artem Agafonov
    ,
    Dmitry Pasechnyuk
    ,
    Alexander V. Gasnikov
    , Martin Takác
  12. Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
    AISTATS 2025 ·
    Ruichen Luo
    ,
    Sebastian U. Stich
    ,
    Samuel Horváth
    , Martin Takác
  13. SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
    NeurIPS 2025 ·
    Ahmed Heakl
    ,
    Yahia Salaheldin Shaaban
    ,
    Salem Lahlou
    , Martin Takác,
    Zangir Iklassov
  14. Uncovering the Spectral Bias in Diagonal State Space Models
    NeurIPS 2025 ·
    Ruben Solozabal
    ,
    Velibor Bojkovic
    ,
    Hilal AlQuabeh
    ,
    Kentaro Inui
    , Martin Takác
  15. Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
    ICLR 2024 ·
    Artem Agafonov
    ,
    Dmitry Kamzolov
    ,
    Alexander V. Gasnikov
    ,
    Ali Kavis
    ,
    Kimon Antonakopoulos
    ,
    Volkan Cevher
    , Martin Takác
  16. Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks
    IJCAI 2024 ·
    Nikita Kotelevskii
    ,
    Samuel Horváth
    ,
    Karthik Nandakumar
    , Martin Takác,
    Maxim Panov
  17. Efficient Conformal Prediction under Data Heterogeneity
    AISTATS 2024 ·
    Vincent Plassier
    ,
    Nikita Kotelevskii
    ,
    Aleksandr Rubashevskii
    ,
    Fedor Noskov
    ,
    Maksim Velikanov
    ,
    Alexander Fishkov
    ,
    Samuel Horváth
    , Martin Takác,
    Eric Moulines
    ,
    Maxim Panov
  18. Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
    NeurIPS 2024 ·
    Artem Agafonov
    ,
    Petr Ostroukhov
    ,
    Roman Mozhaev
    ,
    Konstantin Yakovlev
    ,
    Eduard Gorbunov
    , Martin Takác,
    Alexander V. Gasnikov
    ,
    Dmitry Kamzolov
  19. Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
    NeurIPS 2024 ·
    Sayantan Choudhury
    ,
    Nazarii Tupitsa
    ,
    Nicolas Loizou
    ,
    Samuel Horváth
    , Martin Takác,
    Eduard Gorbunov
  20. Robustly Train Normalizing Flows via KL Divergence Regularization
    AAAI 2024 ·
    Kun Song
    ,
    Ruben Solozabal
    ,
    Hao Li
    , Martin Takác,
    Lu Ren
    ,
    Fakhri Karray
  21. Self-Guiding Exploration for Combinatorial Problems
    NeurIPS 2024 ·
    Zangir Iklassov
    ,
    Yali Du
    ,
    Farkhad Akimov
    , Martin Takác