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
1,369 results for “area:"optimization"” in ICLR 2027. 224 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond One Epoch: Uncertainty-Weighted Sensitivity Regularization for Recommendation Models▲14k3.00
[PDF]Understanding Optimization from Activation and Gradient Spectra: A Modded-NanoGPT Study▼13k2.00
[PDF]Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness▲3952.67
[PDF]LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data▼4.3k2.00
[PDF]Breaking the Quadratic Space Barrier for Optimal Transport via Cost Matrix Compression▼5.9k2.50
[PDF]TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge▲2843.00
[PDF]Breaking the Black Box: An Architecture-Specialized Preconditioning Optimizer for Attention Mechanism▼4.3k2.00
[PDF]Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes▲5103.00
[PDF]Protect Before Evicting: Lagrangian-Guided Encoder Caching for Disaggregated Multimodal LLM Serving▼1361.33
[PDF]A Decentralized Lens on Centralized Federated Learning: Unifying FL via Inexact Douglas–Rachford Splitting▼4.3k2.00
[PDF]Bringing Order to Asynchronous SGD: Towards Optimality under Data-Dependent Delays with Momentum▼5.9k2.50
[PDF]Beating the Worst-Case Per-Iteration Update Time: A Novel Dynamic Network Simplex Method for Optimal Transport▲3.0k2.50
[PDF]Normalization as Control: Batch Normalization Is the Deadbeat Corner of a Kalman-Tuned Normalizer Family▼4.3k2.00
Withdrawn or desk rejected (224)
[PDF]Beyond Training Loss: Full-Space Certificates for Neural JKO and Wasserstein EvolutionDesk rejected
[PDF]Certified Quotient Natural Gradients in Wasserstein Space: Retractions, Ravines, and Higher-Order CollisionsDesk rejected