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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]When Broader Pretraining Hurts In-Context Learning: A Spectral Diagnostic from Inverse Linear Regression▼1361.33
[PDF]WHEN AND HOW DOES A REINFORCEMENT LEARNING OPTIMIZER HELP OUT-OF-DISTRIBUTION DETECTION? A THEORETICAL STUDY▲3.0k2.33
[PDF]Gradient-Descent Based Convergence and Error Analysis of Flow Matching in Deep ReLU Networks▼1.2k1.67
[PDF]Ideal Paths: Geometric Approximation of Logistic Gradient Descent Trajectories at Large Initialization▲13k2.33
[PDF]WHAT EMPIRICAL TRAINING DYNAMICS DO NOT DETERMINE: RELU HISTORIES AND ROBUST PREDICTION SEPARATION▼1361.33
[PDF]Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion▼4.5k2.25
[PDF]Regularized Regression for Hadamard Manifold-Valued Data: Finite-Sample Bounds and Tangent-Space Sparsity▲6.1k2.00
[PDF]Normalization Couples What the Objective Separates: Representation Selection in Group Composition Networks▲143.33
[PDF]Sliding Networks: A Family of Residual Structures Preserving Feature Learning and Feature Diversity▲4.6k3.00
[PDF]A Sharp Finite-Window No-Free-Lunch for Coverage-Sufficient Dependence: Exact Block-Conformal Coverage under Structural Envelopes▼4.3k2.00
[PDF]KREDIT: High-Dimensional Conditional Independence Testing via Kernel-Residualized Distances▼4.3k2.00
[PDF]Query Complexity of Forward-Only Hebbian Learning: Theory and a Native Fit for Diffusion Models▼4.3k2.00
[PDF]Learning Style, Forgetting Semantics: A case study of SFT and RFT on Classification Tasks▲5.4k3.00
[PDF]Learning Stackelberg Equilibria from Preferences over Unknown Multi-Objective Trade-offs▼4.3k2.00
Withdrawn or desk rejected (193)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