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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks▲9.7k2.75
[PDF]RELU NEURAL NETWORK APPROXIMATION TO SMOOTH FUNCTIONAL OPERATOR: DIMENSIONAL DECAY AND ERROR ANALYSIS▲5103.00
[PDF]DataFed: Bid-Agnostic Auctions for Hierarchical Client Selection in Online Federated Edge Learning▼1.3k1.75
[PDF]When Shared Inputs Prevent Heavy Tails from Slowing Model Selection: A Minimax Separation▼4.5k2.67
[PDF]Geometric Capacity of Top- and Sliding-Window Attention: A Theoretical Analysis via Tropical Geometry▼4.3k2.00
[PDF]How Communication Shapes Convergence and Generalization in Decentralized Training: A Feature Learning Perspective▲3952.67
[PDF]Test-time Memory From The Online Learning Perspective: Associative Prediction Game and Regret Optimality▼4.3k2.00
[PDF]Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weakly Communicating▼4.5k2.67
[PDF]Volume Hypothesis or Algorithmic Bias: Margin can Separate Gradient Descent from Random Search▲6.6k3.33
Withdrawn or desk rejected (193)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