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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Identifiability of Nonlinear Multi-view CCA under Partial Latent Observability: Limits and Guarantees of Recovery▲5103.00
[PDF]What Does a Fitted Model Represent? Graded Orders and Sampling Cost in Echo-State Model Spaces▼5.8k2.33
[PDF]Quantum Feature Accessibility as a Mechanism for Shortcut Learning under Distribution Shift.▲6.1k2.00
[PDF]Optimal Depth of Neural Networks: Resource-Correct Stopping with Bounded Logit Increments▼1.2k1.67
[PDF]One Retrieved Token per Step Is Enough: Tight Linear Chain-of-Thought Complexity for Directed Reachability▼2.0k1.00
[PDF]Reference-Centered Generalization Bounds for Modern Pre-Normalized Decoders: Explicit Constants and a Vacuity Threshold▼4.3k2.00
[PDF]Approximation and Generalization Theory of Neural Operator Transformers for Fr\'echet-H\"older Operator Class▲153.33
[PDF]Learning to Switch with Stability and Convergence Guarantees: Policy Gradient for State-Independent Controller Switching in Linear Systems▼1361.33
[PDF]LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction▼4.3k2.00
[PDF]Toward User-centered Agentic Recommendation: When Does Platform Competition Benefit Users?▼4.3k2.00
[PDF]Exploration-Free Learning Needs an Exact Plug-In: Information Floors and Sharp Regret Constants for Event-Triggered Estimation▼1361.33
Withdrawn or desk rejected (193)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