pith. sign in

Gergely Neu

Identifiers

  • name variant Gergely Neu 0.60 · backfill

Papers (25)

  1. Generative Modeling by Value-Driven Transport cs.LG · 2026 · author #3
  2. Online learning with Erd\H{o}s-R\'enyi side-observation graphs stat.ML · 2026 · author #2
  3. Online combinatorial optimization with stochastic decision sets and adversarial losses cs.LG · 2026 · author #1
  4. Efficient learning by implicit exploration in bandit problems with side observations cs.LG · 2026 · author #2
  5. Online learning with noisy side observations cs.LG · 2026 · author #2
  6. Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates cs.LG · 2019 · author #8
  7. Beating SGD Saturation with Tail-Averaging and Minibatching stat.ML · 2019 · author #2
  8. Bandit Principal Component Analysis cs.LG · 2019 · author #2
  9. Potential and Pitfalls of Multi-Armed Bandits for Decentralized Spatial Reuse in WLANs cs.NI · 2018 · author #6
  10. Online Influence Maximization with Local Observations cs.LG · 2018 · author #2
  11. Iterate averaging as regularization for stochastic gradient descent cs.LG · 2018 · author #1
  12. Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence cs.NI · 2018 · author #2
  13. Collaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits cs.NI · 2017 · author #3
  14. On the Hardness of Inventory Management with Censored Demand Data cs.LG · 2017 · author #3
  15. Boltzmann Exploration Done Right cs.LG · 2017 · author #4
  16. A unified view of entropy-regularized Markov decision processes cs.LG · 2017 · author #1
  17. Algorithmic stability and hypothesis complexity stat.ML · 2017 · author #3
  18. Fast rates for online learning in Linearly Solvable Markov Decision Processes cs.LG · 2017 · author #1
  19. Explore no more: Improved high-probability regret bounds for non-stochastic bandits cs.LG · 2015 · author #1
  20. Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits cs.LG · 2015 · author #1
  21. First-order regret bounds for combinatorial semi-bandits cs.LG · 2015 · author #1
  22. Online learning in MDPs with side information cs.LG · 2014 · author #2
  23. An efficient algorithm for learning with semi-bandit feedback cs.LG · 2013 · author #1
  24. Prediction by Random-Walk Perturbation cs.LG · 2013 · author #3
  25. Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods cs.LG · 2012 · author #1

Mentions

  • 1506.03271 #1 · backfill · confidence 0.70 Gergely Neu
  • 1503.05087 #1 · backfill · confidence 0.70 Gergely Neu
  • 1502.06354 #1 · backfill · confidence 0.70 Gergely Neu
  • 1406.6812 #2 · backfill · confidence 0.70 Gergely Neu
  • 1305.2732 #1 · backfill · confidence 0.70 Gergely Neu
  • 1302.5797 #3 · backfill · confidence 0.70 Gergely Neu
  • 1206.5264 #1 · backfill · confidence 0.70 Gergely Neu
  • 2605.22507 #3 · arxiv_oai · confidence 0.70 Gergely Neu

Frequent Coauthors