Copertina

Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yahmed, Ahmed Ben, Calauzènes, Clément, Perchet, Vianney
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting
di: Yahmed, Ahmed Ben, et al.
Pubblicazione: (2025)

Dynamic online matching with budget refills
di: Cherifa, Maria, et al.
Pubblicazione: (2024)

Online matching on stochastic block model
di: Cherifa, Maria, et al.
Pubblicazione: (2025)

On Tradeoffs in Learning-Augmented Algorithms
di: Benomar, Ziyad, et al.
Pubblicazione: (2025)

Non-clairvoyant Scheduling with Partial Predictions
di: Benomar, Ziyad, et al.
Pubblicazione: (2024)

Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
di: Yahmed, Ahmed Ben, et al.
Pubblicazione: (2025)

Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
di: Benomar, Ziyad, et al.
Pubblicazione: (2025)

Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
di: Potfer, Marius, et al.
Pubblicazione: (2025)

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
di: Liu, Xutong, et al.
Pubblicazione: (2022)

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
di: Bertalanič, Blaž, et al.
Pubblicazione: (2026)

DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
di: Garrido-Lucero, Felipe, et al.
Pubblicazione: (2023)

Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
di: Gao, Jing, et al.
Pubblicazione: (2026)

MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP
di: Das, Surajit, et al.
Pubblicazione: (2025)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
di: Fan, Chongyu, et al.
Pubblicazione: (2024)

Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
di: Bouchoucha, Rached, et al.
Pubblicazione: (2024)

Calibrated Forecasting and Persuasion
di: Jain, Atulya, et al.
Pubblicazione: (2024)

Instance-dependent Stochastic Lipschitz bandit
di: Potfer, Marius, et al.
Pubblicazione: (2026)

A survey on multi-player bandits
di: Boursier, Etienne, et al.
Pubblicazione: (2022)

Provably Efficient Exploration in Reward Machines with Low Regret
di: Bourel, Hippolyte, et al.
Pubblicazione: (2024)

Two-Sided Time-Independent Regret for Matching Markets with Limited Interviews
di: Mirfakhar, Amirmahdi, et al.
Pubblicazione: (2026)

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms
di: Xu, Mengfan, et al.
Pubblicazione: (2020)

Agentic AI and the Cyber Arms Race
di: Oesch, Sean, et al.
Pubblicazione: (2025)

Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making
di: Dai, Siyuan, et al.
Pubblicazione: (2025)

Contextual Combinatorial Bandits with Probabilistically Triggered Arms
di: Liu, Xutong, et al.
Pubblicazione: (2023)

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
di: Lasby, Mike, et al.
Pubblicazione: (2025)

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
di: Fluri, Lukas, et al.
Pubblicazione: (2024)

Improved Algorithms for Contextual Dynamic Pricing
di: Tullii, Matilde, et al.
Pubblicazione: (2024)

Energy-Efficient Sleep Mode Optimization of 5G mmWave Networks Using Deep Contextual MAB
di: Masrur, Saad, et al.
Pubblicazione: (2024)

The Adaptive Arms Race: Redefining Robustness in AI Security
di: Tsingenopoulos, Ilias, et al.
Pubblicazione: (2023)

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
di: Vakili, Sattar, et al.
Pubblicazione: (2024)

Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives
di: Shao, Jiaqi, et al.
Pubblicazione: (2024)

Adaptive Bandit Algorithms for Contextual Matching Markets
di: Lin, Shiyun, et al.
Pubblicazione: (2026)

Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight
di: Yellin, Ben, et al.
Pubblicazione: (2026)

Learning in Prophet Inequalities with Noisy Observations
di: Kim, Jung-hun, et al.
Pubblicazione: (2026)

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
di: Rutherford, Alexander, et al.
Pubblicazione: (2024)

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
di: Borchmann, Łukasz, et al.
Pubblicazione: (2026)

The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods
di: Laurier, Linda, et al.
Pubblicazione: (2024)

FOSSIL: Regret-Minimizing Curriculum Learning for Metadata-Free and Low-Data Mpox Diagnosis
di: Han, Sahng-Min, et al.
Pubblicazione: (2025)

On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
di: Shah, Anvay, et al.
Pubblicazione: (2026)

Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
di: Bai, Qinbo, et al.
Pubblicazione: (2023)