pith. sign in

Martin Tak\'a\v{c}

Identifiers

  • name variant Martin Tak\'a\v{c} 0.60 · backfill

Papers (44)

  1. Dual Advantage Fields cs.LG · 2026 · author #7
  2. Convex Compositional Reasoning Models cs.LG · 2026 · author #9
  3. Decentralized Inexact Cubic Newton Method with Consensus Procedure math.OC · 2026 · author #7
  4. LionMuon: Alternating Spectral and Sign Descent for Efficient Training cs.LG · 2026 · author #6
  5. Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters cs.LG · 2026 · author #3
  6. Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition math.OC · 2026 · author #3
  7. Heterogeneous-Horizon Exact-Weight Local SGD math.OC · 2026 · author #2
  8. Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models cs.SD · 2026 · author #5
  9. Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers cs.LG · 2026 · author #4
  10. Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods cs.LG · 2025 · author #6
  11. Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems math.OC · 2025 · author #3
  12. Learning Latent Graph Geometry via Fixed-Point Schr\"odinger-Type Activation: A Theoretical Study cs.LG · 2025 · author #2
  13. MirrorCheck: Efficient Adversarial Defense for Vision-Language Models cs.CV · 2024 · author #5
  14. Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework cs.LG · 2019 · author #4
  15. Active Metric Learning for Supervised Classification cs.LG · 2018 · author #5
  16. Reinforcement Learning for Solving the Vehicle Routing Problem cs.AI · 2018 · author #4
  17. SGD and Hogwild! Convergence Without the Bounded Gradients Assumption math.OC · 2018 · author #6
  18. An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning math.OC · 2017 · author #5
  19. Stock-out Prediction in Multi-echelon Networks cs.LG · 2017 · author #3
  20. Stochastic Recursive Gradient Algorithm for Nonconvex Optimization stat.ML · 2017 · author #4
  21. SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient stat.ML · 2017 · author #4
  22. Applying Deep Learning to the Newsvendor Problem cs.LG · 2016 · author #3
  23. Distributed Hessian-Free Optimization for Deep Neural Network cs.LG · 2016 · author #4
  24. A Multi-Batch L-BFGS Method for Machine Learning math.OC · 2016 · author #3
  25. Distributed Inexact Damped Newton Method: Data Partitioning and Load-Balancing cs.LG · 2016 · author #2
  26. Primal-Dual Rates and Certificates cs.LG · 2016 · author #3
  27. Distributed Optimization with Arbitrary Local Solvers cs.LG · 2015 · author #7
  28. Partitioning Data on Features or Samples in Communication-Efficient Distributed Optimization? math.OC · 2015 · author #2
  29. Dual Free Adaptive Mini-batch SDCA for Empirical Risk Minimization math.OC · 2015 · author #2
  30. Distributed Mini-Batch SDCA cs.LG · 2015 · author #1
  31. Linear Convergence of the Randomized Feasible Descent Method Under the Weak Strong Convexity Assumption cs.LG · 2015 · author #3
  32. Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting cs.LG · 2015 · author #4
  33. On the Complexity of Parallel Coordinate Descent math.OC · 2015 · author #2
  34. Adding vs. Averaging in Distributed Primal-Dual Optimization cs.LG · 2015 · author #6
  35. SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization cs.LG · 2015 · author #3
  36. mS2GD: Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting cs.LG · 2014 · author #4
  37. Communication-Efficient Distributed Dual Coordinate Ascent cs.LG · 2014 · author #3
  38. Fast Distributed Coordinate Descent for Non-Strongly Convex Losses math.OC · 2014 · author #4
  39. TOP-SPIN: TOPic discovery via Sparse Principal component INterference cs.CV · 2013 · author #1
  40. On Optimal Probabilities in Stochastic Coordinate Descent Methods stat.ML · 2013 · author #2
  41. Distributed Coordinate Descent Method for Learning with Big Data stat.ML · 2013 · author #2
  42. Mini-Batch Primal and Dual Methods for SVMs cs.LG · 2013 · author #1
  43. Parallel Coordinate Descent Methods for Big Data Optimization math.OC · 2012 · author #2
  44. Iteration Complexity of Randomized Block-Coordinate Descent Methods for Minimizing a Composite Function math.OC · 2011 · author #2

Mentions

  • 1507.08322 #1 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 2606.04188 #7 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 1506.02530 #3 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1504.04407 #4 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1503.03033 #2 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1502.03508 #6 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1502.02268 #3 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1410.4744 #4 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1409.1458 #3 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1405.5300 #4 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1311.1406 #1 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1310.3438 #2 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1310.2059 #2 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1303.2314 #1 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 1212.0873 #2 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 2605.23395 #9 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 2406.09250 #5 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 2605.21169 #7 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 1107.2848 #2 · backfill · confidence 0.70 Martin Tak\'a\v{c}
  • 2605.19811 #6 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 2602.05813 #4 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}
  • 2510.10777 #6 · arxiv_oai · confidence 0.70 Martin Tak\'a\v{c}

Frequent Coauthors