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
47 results for “keyword:"learning rate"” in ICLR 2027. 12 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Automated Hyperparameter Configuration Selection for Distantly Supervised NER using Reinforcement Learning and Bayesian Optimization▼12k1.67
[PDF]IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback▼1.2k1.67
[PDF]What Does a Training Token Buy? Contextual Information Gain Beyond Perplexity Across Open Model Suites▼1.2k1.67
[PDF]The Spectral Shortcut: How a Fast Contextual Pathway Suppresses Spectral Learning in Serial Spectral–Spatial Models▼4.3k2.00
[PDF]Convergence of Large-Stepsize SGD for the Cross-entropy Loss via Stochastic Lyapunov Stability▼1.2k1.67
[PDF]Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons▼4.3k2.00
[PDF]Self-Tuned Q-Learning and SARSA: Policy Control Without Worrying About Step-Size Calibration▼1.2k1.67
[PDF]Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and the Cost Against Classical Selection▲11.00
[PDF]When Does Learning-Rate Retuning Help? Attainable Output Geometry Under a Fixed Update Budget▼5.8k2.33
[PDF]Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training▲20k2.67
Withdrawn or desk rejected (12)
[PDF]When and How Often to Defend? On the Overlooked Role of Learning Rate Schedules in PoisoningWithdrawn1.33