No article text was recorded for this version.
memory-regret phase transition
Version 1 of 138 papers66 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Tight Gap-Dependent Memory-Regret Trade-Off for Single-Pass Streaming Stochastic Multi-Armed Bandits
- Blog: Near Optimal Memory-Regret Tradeoff for Online Learning
- Blog: Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits
- Blog: Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality
- Blog: Conditional Swap Regret and Conditional Correlated Equilibrium
- Blog: Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits
- Blog: Online Learning with Bounded Recall
- Blog: Bounded Rationality in Las Vegas: Probabilistic Finite Automata Play Multi-Armed Bandits
- Blog: Online Learning with Graph-Structured Feedback against Adaptive Adversaries
- Blog: Generalized Linear Bandits with Memory
- Blog: Online Convex Optimization with Unbounded Memory
- Blog: Online Learning with Switching Costs and Other Adaptive Adversaries
- Blog: A Sharp Memory-Regret Trade-off for Multi-Pass Streaming Bandits
- Blog: Online Recommendations for Agents with Discounted Adaptive Preferences
- Blog: Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization
- Blog: Exponential Weights Algorithms for Selective Learning
- Blog: Tight Memory-Regret Lower Bounds for Streaming Bandits
- Blog: Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
- Blog: Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
- Blog: Online learning with graph-structured feedback against adaptive adversaries
- Blog: Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs
- Blog: Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory
- Blog: Improved Space Bounds for Learning with Experts
- Blog: Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback
- Blog: Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
- Blog: Solving multi-model MDPs by coordinate ascent and dynamic programming
- Blog: Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
- Blog: Online Forgetting Process for Linear Regression Models
- Blog: Improved Space Bounds for Learning with Experts
- Blog: Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games
- Blog: Online Prediction in Sub-linear Space
- Blog: Learning what to remember
- Blog: Minimax-Optimal Policy Regret in Partially Observable Markov Games
- Blog: History-Restricted Online Learning
- Blog: Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
- Blog: Restless dependent bandits with fading memory
- Blog: Stochastic Multi-armed Bandits in Constant Space
- Blog: Learning what to remember
History & citation
Current · Permanent link
- Policy Regret for Learning Against Adaptive Adversaries merged into this direction (60% overlap)
- Online Learning with Limited Memory and Bounded Recall merged into this direction (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_memory_regret_phase_transition_44594fd6,
title = {memory-regret phase transition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/memory-regret-phase-transition/rdr_44594fd69e94497981577e54dfb98e02},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_memory_regret_phase_transition_44594fd6_v1,
title = {memory-regret phase transition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/memory-regret-phase-transition/rdr_44594fd69e94497981577e54dfb98e02/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}