← Authors

Martin Takac

47 papers · 2013–2026 · 13 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (12) 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (13) 🐝 Cross-Pollinator (10) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (17) πŸ† Keyword Champion πŸš€ Conference Pioneer ⚑ Prolific Year (7) πŸ—ƒοΈ Keyword Collector (147) πŸ“ˆ Trend Setter πŸ’Ž Century Club (46) πŸ”₯ Unstoppable (13)

Conferences

ICML (9) NIPS (9) ICLR (7) AISTATS (5) JMLR (5) IJCAI (3) AAAI (2) ACL (2) AACL (1) ACML (1) EACL (1) IJCNLP (1) MICCAI (1)

Top co-authors

Peter Richtarik (10) Samuel HorvΓ‘th (9) Alexander Gasnikov (8) Eduard Gorbunov (6) Aleksandr Beznosikov (5) Dmitry Kamzolov (5) Martin Jaggi (4) Zangir Iklassov (4) Marek Suppa (4) Chenxin Ma (4)

Research topics

Reinforcement Learning (1)

Keywords

stochastic optimization (7) distributed optimization (6) stochastic gradient descent (5) stochastic gradient (4) communication efficiency (4) empirical risk minimization (4) distributed learning (3) linear convergence (3) variational inequality (3) primal-dual optimization (3) low-resource language (3) federated learning (3) parallel computing (2) reinforcement learning (2) continuous optimization (2) machine learning (2) convergence analysis (2) active learning (2) sentiment analysis (2) uncertainty quantification (2)

Papers

Bant: Byzantine Antidote via Trial Function and Trust Scores AAAI 2026
Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages AACL 2025
Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles ACL 2025
When the Dictionary Strikes Back: A Case Study on Slovak Migration Location Term Extraction and NER via Rule-Based vs. LLM Methods ACL 2025
MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search MICCAI 2025
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training ICML 2025
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed ICML 2025
Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages IJCNLP 2025
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis AISTATS 2025
OPTAMI: Global Superlinear Convergence of High-order Methods ICLR 2025
Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity ICLR 2025
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization ICLR 2025
From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation ICLR 2025
Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness ICLR 2024
Robustly Train Normalizing Flows via KL Divergence Regularization AAAI 2024
Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks IJCAI 2024
Efficient Conformal Prediction under Data Heterogeneity AISTATS 2024
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad NIPS 2024
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations NIPS 2024
Self-Guiding Exploration for Combinatorial Problems NIPS 2024
Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities NIPS 2023
Byzantine-Tolerant Methods for Distributed Variational Inequalities NIPS 2023
Reinforcement Learning for Solving Stochastic Vehicle Routing Problem ACML 2023
Algorithm for Constrained Markov Decision Process with Linear Convergence AISTATS 2023
WikiGoldSK: Annotated Dataset, Baselines and Few-Shot Learning Experiments for Slovak Named Entity Recognition EACL 2023
SP2 : A Second Order Stochastic Polyak Method ICLR 2023
On the Study of Curriculum Learning for Inferring Dispatching Policies on the Job Shop Scheduling IJCAI 2023
A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate NIPS 2022
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information ICLR 2022
The power of first-order smooth optimization for black-box non-smooth problems ICML 2022
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm AISTATS 2021
Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy AISTATS 2020
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning JMLR 2020
Entropy-Penalized Semidefinite Programming IJCAI 2019
New Convergence Aspects of Stochastic Gradient Algorithms JMLR 2019
CoCoA: A General Framework for Communication-Efficient Distributed Optimization JMLR 2018
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption ICML 2018
Reinforcement Learning for Solving the Vehicle Routing Problem NIPS 2018
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient ICML 2017
A Multi-Batch L-BFGS Method for Machine Learning NIPS 2016
Primal-Dual Rates and Certificates ICML 2016
SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization ICML 2016
Distributed Coordinate Descent Method for Learning with Big Data JMLR 2016
Linear Convergence of Randomized Feasible Descent Methods Under the Weak Strong Convexity Assumption JMLR 2016
Adding vs. Averaging in Distributed Primal-Dual Optimization ICML 2015
Communication-Efficient Distributed Dual Coordinate Ascent NIPS 2014
Mini-Batch Primal and Dual Methods for SVMs ICML 2013