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
64 results for “keyword:"hyperparameter"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]How Many, Not Which: Automatic Data Budgets for Conditional GANs Using Gradient Spectra▼1.2k1.67
[PDF]Automated Hyperparameter Configuration Selection for Distantly Supervised NER using Reinforcement Learning and Bayesian Optimization▼12k1.67
[PDF]RULER: Reasoning from Trials to Transferable Rules for Finite-Budget Online Algorithm Configuration▼4.5k2.67
[PDF]Sliding Networks: A Family of Residual Structures Preserving Feature Learning and Feature Diversity▲4.6k3.00
[PDF]Training Recipes Leak Through Behavioral Fingerprints in Text-to-Image Diffusion Models▼4.5k2.67
[PDF]Searching Harder Hurts at a Fixed Budget: The Unreported Candidate-Set Size in Adaptive Collocation▼1.2k1.67
[PDF]Optimizer-dependent training dynamics converge to the same one-third optimal data scaling▲3.0k2.33
[PDF]Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons▼4.3k2.00
[PDF]The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It▼5.8k2.33
[PDF]Provably Efficient Algorithm Configuration with Local Structure and Reuse of Observations▲4052.67
[PDF]Beyond Final Regret: Stress-Testing Hyperparameter Optimization Conclusions Across Evaluation Regimes▼1351.33
[PDF]GraphSieve: Graph Purification via Attack-Agnostic Calibration across Perturbation Severities▼4.3k2.00
[PDF]Sampler Gains Shrink to Noise Under Equal Tuning Budgets: The Winner's Curse in LLM Decoding Evaluation▼1351.33
[PDF]Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer▼1.2k3.00
[PDF]Dynamic Optimisation of Discount and Trace Decay for Value-Based Reinforcement Learning▲5103.00
Withdrawn or desk rejected (8)
[PDF]CONTRAST-LEVEL POSTERIOR REGRET CERTIFICATES FOR QUADRATIC COMPOSITES WITH UNCERTAIN GP HYPERPARAMETERSWithdrawn1.50
[PDF]CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient SearchWithdrawn2.00