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
213 results for “keyword:"learning theory"” in ICLR 2027. 27 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Quantum Algorithms for Risk-Sensitive Bandits: Matching Upper and Lower Bounds for Quantum CVaR Estimation▼4.5k2.67
[PDF]Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations▼5.8k2.33
[PDF]Constrained Polynomial Probabilistic Zonotopes: When Can One Compressed Model Serve Many Tasks?▼1.2k1.67
[PDF]When Can Old Evaluations Certify a New Model? Matching Label-Complexity Bounds Under Evaluator-Residual Drift▼4.5k2.67
[PDF]Simultaneously Perturbed Optimistic Gradient Methods for Payoff-Based Learning in Games▲9.2k2.67
[PDF]A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping▼4.5k2.67
[PDF]Tight Mistake–Abstention Tradeoffs for Sequential Prediction under Adversarial Injections▼2443.33
[PDF]What Must Be Learned to Adapt? Decision-Directed Identification Under Environment Shift▼4.3k2.00
[PDF]Acting Is Easier Than Adapting: The Geometry and Design of Adaptation-Sufficient Representations▼1361.33
[PDF]Learning Long-Horizon Flow Maps in High Dimensions: From a Regression Surrogate to Efficient Statistical Learning▲3952.67
[PDF]A Framework for Analyzing DNN Representation Quality: Dynamics of Interaction Generalizability▼71.25
[PDF]Two Timescales of Forgetting in Fine-tuning of Language Models: Fast Behavioral Suppression and Slow Representational Drift▲2843.00
[PDF]What Does Neural Collapse Indicate for Generalization?: A Singular Learning Theory Perspective▲3.9k1.67
Withdrawn or desk rejected (27)
[PDF]Stability and Generalization of Noisy signSGD: From Sign Discontinuity to Gaussian SmoothingWithdrawn
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00
[PDF]When Does an Observable Lose Failure Evidence? Exact Ranking Losses for Runtime Detection in Vision–Language–Action PoliciesWithdrawn1.00
[PDF]The Knowability Gap: Auditing When Better Models Cannot Replace Missing InformationDesk rejected
[PDF]WHEN BATCH SCHEDULES CANNOT BE CERTIFIED: CAPACITY OF GLOBALLY VALID MONOMIAL CERTIFICATES ON INTEGER LOG-HULLSWithdrawn1.33