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
1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]UNCERTAINTY QUANTIFICATION OF RIEMANNIAN LOW-RANK TENSOR BANDITS WITH ROTATED ELIM- INATION▼4.3k2.00
[PDF]Efficient Online Reinforcement Learning with All-Policy Linear -Realizability and Sparse Stochastic Transitions▼1.2k3.00
[PDF]The Decision Value of Imperfect Provenance: A Minimax Characterization for Shadow Evaluation▼1.2k3.00
[PDF]Asymptotic Analysis of Empirical Risk Minimization on Entrywise i.i.d. Heavy-Tailed Data▼4.5k2.67
[PDF]A VC-Dimension View of Capacity and Generalization in Quantum Machine Learning with Classical Data▼1.2k1.67
[PDF]Alignment, Not Isotropy: Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning▼1.2k1.67
[PDF]The Fates’ Spindle: Rotation Representation Emerges for Relative Position in Transformer▼12k1.67
[PDF]Persistent-Cache Complexity: A Finite-State And Communication-Theoretic View of Causal Decoders▲3952.67
[PDF]Learning Where and What to Optimize: From Diffusion Distillation to Reinforcement Learning▲432.75
[PDF]When Do Structured Prompts Help In-Context Learning? A Relevance–Redundancy Theory of In-Context Prediction▲5.4k3.00
Withdrawn or desk rejected (193)
[PDF]Curvature Controlled Mixing on the Interpolation Manifold: Sharp Cutoffs in Late-Phase Training DynamicsDesk rejected
[PDF]Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear RegressionDesk rejected