conftrace_

preconditioners

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sgd (2) gradient descent (2) feature learning (2) adamw (1) flexible conjugate gradient (1) o(n) operations (1) fix-point iterative algorithms (1) linear looped transformers (1) population training loss (1) sparsification (1)

Papers

Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nyström Method COLT 2025 LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently ICML 2025 On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning ICML 2025 Structured Preconditioners in Adaptive Optimization: A Unified Analysis ICML 2025 Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? ICML 2024 Error Feedback Can Accurately Compress Preconditioners ICML 2024 Neural operators meet conjugate gradients: The FCG-NO method for efficient PDE solving ICML 2024 Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models ICML 2024