NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
177 results for “keyword:"bandits"” in ICLR 2027. 32 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Task-Conditioned Quality Learning for Heterogeneous and Unreliable Multi-Agent Systems▼5.8k2.33
[PDF]Safe Contextual Pricing under Censored Feedback: Joint Inventory and Allocation with Online Conformal Guarantees▼1.2k1.67
[PDF]Provably Efficient Algorithm Configuration with Local Structure and Reuse of Observations▲3952.67
[PDF]BRINE: Matched-State Counterfactual Supervision for Risk-Aware Cognitive Routing in Underwater Robots▼1361.33
[PDF]Sketch-Aware Generalized Linear Bandits: Efficient One-Pass Updates via Frequent Directions▼4.5k2.67
[PDF]Beyond Global Clusters: Objective-Specific User Clustering for Multi-Objective Bandits▼5.8k2.33
[PDF]Non-Asymptotic Last-Iterate Convergence for Scale-Invariant Regret-Matching Algorithms in Matrix Games▼5.8k2.33
[PDF]Online Graph Classification with One-Bit Feedback: A Graph Convolutional Bandit Approach▼1.2k3.00
[PDF]Optimal Posterior Sampling for Fixed-Budget Cluster Identification through Pairwise Observations▼1.2k3.00
[PDF]Improved Regret and Violation Guarantees for Constrained Contextual Bandits with General Realizability▼4.5k2.67
[PDF]Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback▲3952.67
[PDF]Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities▼4.3k2.00
[PDF]Queue-Aware Combinatorial Bandit Scheduling for Speculative Decoding in Cloud–Edge LLM Serving▲4.6k3.00
[PDF]Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards▼4.5k2.67
[PDF]Investor-Specific Multi-Objective Preference Alignment for Personalized Portfolio Optimization▲3.0k2.33
[PDF]Information-Theoretic Analysis of Multi-Objective Bandits: Pareto Violations and Gap-Based Regret▲6.1k2.00
Withdrawn or desk rejected (32)
[PDF]What to Try, Where to Try It: Online Adaptive Search Policies for Machine Learning Agents.Withdrawn1.33
[PDF]FidelityFlow-PO: Bandit-Guided Allocation of Context Fidelity for Long-Context DPODesk rejected
[PDF]Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language ModelsWithdrawn2.00