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
50 results for “keyword:"momentum"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Tight Convergence Analysis of Alternating Gradient Descent-Ascent with Negative Momentum via Parametric SDPs▼4.5k2.67
[PDF]The Implicit Bias of Mirror Descent on Multiclass Separable Data: Stochasticity and Momentum▼1.1k3.25
[PDF]Inverse-Free Second-Order Momentum for Decentralized Riemannian Stochastic Optimization on Compact Submanifolds▲3.8k2.50
[PDF]Not All Blocks Need Full Momentum: Sharpness-Aware Memory-Efficient Optimization for Transformers▼4.3k2.00
[PDF]Beyond Instantaneous Gradients: Momentum-Guided Adaptive Gradient Masking for Sparse Fine-Tuning of LLMs▼1.2k1.67
[PDF]Zeroth-Order Momentum and Adaptive Methods for Nonsmooth Policy Optimization from Human Preferences▲5.4k3.00
[PDF]Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency▼1.2k3.00
[PDF]Implicit Sparse Regularization in Momentum Gradient Descent: A Shifted Early Stopping Window Induced by Momentum and Depth▼4.3k2.00
[PDF]Subject Identity as a Shortcut: Rethinking Self-Supervised Pretraining for EEG Foundation Models▲6.1k2.00
[PDF]Backpropagated Output Momentum: Relocating Optimizer History from Parameters to Task Space▲5103.00
[PDF]Momentum Makes (Adaptive) Subgradient Methods Optimal for Stochastic Nonsmooth Nonconvex Optimization▼5.8k2.33