Regret

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

2 new papers

A weekly snapshot of new work published in Regret.

Period ending 2026-09-14

8 new papers

A weekly snapshot of new work published in Regret.

Period ending 2026-09-07

4 new papers

A weekly snapshot of new work published in Regret.

Inside this field

Focused directions

Focused topic

Regret

Within Regret

100 papersExplore

Focused topic

Linear Regret

Within Regret

83 papersExplore

Focused topic

O(T^Β)$ Simultaneous Regret

Within Regret

34 papersExplore

Focused topic

Near-Optimal Regret Guarantees

Within Regret

22 papersExplore

201 papers

Latest in Regret

Browse all topics →

Adaptive Bayes exactly tracks information over intrinsic time
Jun 26, 2026Akshay BalsubramaniLinear Regret Bayesian
Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes
Jun 26, 2026Luis LealNash Equilibrium Imperfect-Information Games
Learning in Markovian bandits with non-observable states and constrained decision epochs
Jun 25, 2026Thomas Hira, Victor Boone, Urtzi Ayesta +1O(T^Β)$ Simultaneous Regret Markov Decision Processes
Blackwell Approachability and Gradient Equilibrium are Equivalent
Jun 25, 2026Brian W. Lee, Nika Haghtalab, Michael I. Jordan +1Equilibrium Regret
Leveraging Similarities in Multi-Armed Bandits
Jun 22, 2026Khaled Eldowa, Thibaud Rahier, Augustin Cablant +2Multi-Armed Bandits Regret
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
Jun 22, 2026Suyash MishraPareto Frontier Situation
Selective Ensemble Based on Preference-Directed Multi-Objective Bandits
Jun 20, 2026Lanjihong Ma, Zhen-Yu Zhang, Masashi Sugiyama +1Multi-Armed Bandits Pareto Frontier
Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning
Jun 18, 2026Asaf Cassel, Aviv RosenbergEfficient Exploration Multi-Armed Bandits
Optimal Coarse Correlated Equilibria in Mean Field Games: Linear Programming and No-Regret Learning
Jun 18, 2026Luciano Campi, Federico Cannerozzi, Ioannis TzouanasEquilibrium Mean-Field Limit
Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses
Jun 18, 2026Zhuoyu Cheng, Kohei Hatano, Eiji TakimotoConvex Optimization Convex Sets
A Solver-Free Training Method for Predict-then-Optimize
Jun 17, 2026Beichen Wan, Mo LiuLearning-Augmented Algorithms Llm-Based Optimization Modeling
Toward Simultaneously Optimal Regret in U-Calibration
Jun 16, 2026Rafael Frongillo, Haipeng Luo, Nishant A. Mehta +1Linear Regret Regret
Sequential Hiring of Contingent Workers Through Learning-Based Optimization
Jun 16, 2026Chris Lee, Xiuli Chao, Izak DuenyasStochastic Delays Optimal Bandit Algorithms
Decision-Weighted Flow Matching for Contextual Stochastic Optimization
Jun 15, 2026Jize Xie, Haomiao Wu, Qiang Chen +2Conditional Flow Matching Stochastic Optimization
Near-Optimal Stochastic Linear Bandits with Delay
Jun 15, 2026Ofir Schlisselberg, Mengxiao Zhang, Yishay MansourLinear Bandits Near-Optimal Regret Guarantees
Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret
Jun 15, 2026Madhulatha Mandarapu, Sandeep KunkunuruApproximate Nearest-Neighbor Search Selectivity
When Does q-error Predict Plan Regret? Three Regimes of Cardinality-Estimation Error
Jun 14, 2026Madhulatha Mandarapu, Sandeep KunkunuruReward-Prediction Error Estimators
Repeated Bilateral Trade: The Quest for Fairness
Jun 13, 2026François Bachoc, Roberto Colomboni, Emilie KaufmannNash Equilibrium Market
Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
Jun 12, 2026Yan Dai, Negin Golrezaei, Patrick JailletLarge-Scale Recommendation Systems Optimal Bandit Algorithms
Online Convex Optimization with Sublinear Noisy Probes
Jun 12, 2026Simone Di Gregorio, Anupam Gupta, Stefano Leonardi +1O(T^Β)$ Simultaneous Regret Convex Optimization
Learning with Simulators: No Regret in a Computationally Bounded World
Jun 11, 2026Sasha Voitovych, Abhishek Shetty, Noah Golowich +1Regret
Capacity-Constrained Online Convex Optimization with Delayed Feedback
Jun 10, 2026Alexander Ryabchenko, Idan Attias, Daniel M. RoyO(T^Β)$ Simultaneous Regret Convex Optimization
Data-Driven Dynamic Assortment in Online Platforms: Learning about Two Sides
Jun 9, 2026Rahul Roy, Nur Sunar, Jayashankar M. SwaminathanLinear Regret Semiparametric Framework
Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
Jun 8, 2026Udvas Das, Waris Radji, Debabrota Basu +1Optimal Bandit Algorithms Linear Bandits
A Regret Minimization Framework on Preference Learning in Large Language Models
Jun 8, 2026Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim +4Reinforcement Learning From Human Feedback Preference Learning
Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees
Jun 8, 2026Deqi Zheng, Xiaoyang Xu, Yuhong YangLinear Bandits Multi-Armed Bandits
Evaluating AI Investment Strategies
Jun 7, 2026Irene AldridgeAlgorithm Auditing Linear Regret
Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization
Jun 6, 2026Wentao Zhang, Yutong Zhang, Wentao MoConvex Optimization Linear Regret
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
Jun 5, 2026Qianqian Lei, Soham Bonnerjee, Yuefeng Han +1Generalization Bounds Lipschitz Constant
Learn to Match: Two-Sided Matching with Temporally Extended Feedback
Jun 4, 2026Haijing Zong, Yancheng Liang, Boyang Zhou +1Bipartite Perfect Matchings Matching Markets
Regret Minimization with Adaptive Opponents in Repeated Games
Jun 4, 2026Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu +1Regret Game Theory
Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis
Jun 3, 2026Juan M. HuertaWikipedia Procedural Knowledge
Two-Action Apple Tasting with Switching Costs
Jun 2, 2026Tommaso Cesari, Roberto ColomboniO(T^Β)$ Simultaneous Regret
Online Learning with Gradient-Variation Interval Regret
Jun 2, 2026Yan-Feng Xie, Shuche Wang, Peng Zhao +1Learning-Augmented Algorithms Linear Regret
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
Jun 2, 2026Mingkuan Zhao, Xiayu Sun, Wentao Hu +5Contextual Grounding Prior Knowledge
From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
Jun 1, 2026Moses Charikar, Chirag Pabbaraju, Ambuj TewariConvex Optimization Curvature-Aware Quadratic Banks
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Jun 1, 2026Zhiming Xu, Weitao Zhou, Xianghui Pan +4Latent Cluster Geometry Linear Regret
AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
Jun 1, 2026Saptarishi Dhanuka, Sarvesh Iyer, Manmeet Singh +5Artificial Intelligence Weather Models Linear Regret
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
Jun 1, 2026Pu Wang, Yao-Xiang DingBandits Linear Regret
Coherent Swap Regret and Channel-Proof Learning
Jun 1, 2026Sohail SarkarPost-Quantum Cryptography O(T^Β)$ Simultaneous Regret
Efficient Exploration for Iterative Nash Preference Optimization
May 31, 2026Tianlong Nan, Xiaopeng Li, Christian Kroer +1Reinforcement Learning From Human Feedback Exploration-Exploitation Dilemma
Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
May 31, 2026Shion TakenoBayesian Optimization Variance Reduction
Online Packet Scheduling with Deadlines and Learning
May 30, 2026Gianmarco Genalti, Achraf Azize, Vianney PerchetNear-Optimal Regret Guarantees Deadlines
Variance-sensitive Thompson sampling for generalised linear bandits, revisited
May 29, 2026Tom Perneczky, Marc Abeille, David JanzThompson Sampling Near-Optimal Regret Guarantees
Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
May 29, 2026Catherine Chen, Jingyan Shen, Zhun Deng +1Conditional-Value-At-Risk Conformal Risk Control
Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
May 29, 2026Ivan Lau, Daniel McMorrow, Kevin Jamieson +1O(T^Β)$ Simultaneous Regret Well-Tuned Static Batching Policy
Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
May 28, 2026Mark WalshLinear Regret Sufficient Conditions
Instance-dependent Stochastic Lipschitz bandit
May 28, 2026Marius Potfer, Vianney PerchetLipschitz Constant Multi-Armed Bandits
Optimality of Sequential Filtering Under Independent Cost and Selectivity Models
May 28, 2026Hrishikesh Paranjape, Abhishek Mandal, Xian SunOrder Matters Sequential Decision Making
TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
May 27, 2026Chusen Li, Zhou Liu, Shuigeng Zhou +1Deep Reinforcement Learning Group Relative Policy Optimization
Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation
May 27, 2026Wonyoung Kim, Min-Hwan Oh, Garud Iyengar +1Near-Optimal Regret Guarantees Markov Decision Processes
Adaptive Bandit Algorithms for Contextual Matching Markets
May 27, 2026Shiyun Lin, Simon Mauras, Vianney Perchet +1Near-Optimal Regret Guarantees Bandits
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
May 27, 2026Zhi Zhou, Ming Yang, Shi-Yu Tian +3Stable Test-Time Adaptation Non-Stationarity
Decentralized Parameter-Free Online Learning with Compressed Gossip
May 27, 2026Tomas Ortega, Hamid JafarkhaniLearning-Augmented Algorithms Near-Optimal Regret Guarantees
Near-Optimal Regret in Adversarial Kernel Bandits
May 26, 2026Yu-Jie Zhang, Hao Qiu, Jonathan Scarlett +1Kernel Hilbert Spaces Regret
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
May 25, 2026Anas Barakat, Andreas Kontogiannis, Vasilis Pollatos +2O(T^Β)$ Simultaneous Regret Convex Optimization
On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
May 25, 2026Yunlong Hou, Zixin Zhong, Vincent Y. F. TanMulti-Armed Bandits Linear Bandits
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
May 22, 2026Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-GkaragkounisBandits Delay
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
May 22, 2026Manish Aryal, Faiyaz Azam, Agnivo Banerjee +11Entropy Regularized Reinforcement Learning Deep Reinforcement Learning
Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing
May 22, 2026Shugang Hao, Lingjie DuanCrowdsourced Framework Large Language Model Fine-Tuning

Jun 26, 2026 · cs.LGJ/K move · Enter open · S save

Adaptive Bayes exactly tracks information over intrinsic time

Akshay Balsubramani

Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such update obeys an exact information-accounting identity. On each round, the learner's excess loss to any chosen comparator is the sum of an immediate payment for the uncertainty exposed by the round and a reduction in the information distance from the learner's current weights to the comparator. The cumulative payment defines a pathwise uncertainty clock, the \emph{intrinsic time} of the realized sequence. Summing one-step balances yields two exact adaptive decompositions of cumulative regret, one for each natural way of composing the update across rounds. Because the decompositions are exact rather than upper bounds, favorable stochastic or low-noise regimes appear as self-bounding properties of the realized intrinsic time, not as slack in worst-case analyses. The same calculus covers Hedge, optimistic and side-information variants, continuous priors, boosting, online convex optimization, contextual bandits, and repeated games: the pathwise account is the same in every case.

Linear Regret Bayesian Feedback Loop Prior Knowledge

Open paper Ask about it PDF