{"total":19,"rows":[{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2505.19227","title":"Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law","created":"2025-05-25","cited_by_count":24,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2411.01803","title":"Gradient Methods with Online Scaling","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2505.24399","title":"LightSAM: Parameter-Agnostic Sharpness-Aware Minimization","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2411.05033","title":"Diagonalization without Diagonalization: A Direct Optimization Approach for Solid-State Density Functional Theory","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2601.20769","title":"Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2605.00650","title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2602.09395","title":"Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2607.22929","title":"Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.22129","title":"Blockwise Stabilized Adaptive Cubic Regularization with Subsolvers via Recurrence","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2412.10362","title":"OP-LoRA: The Blessing of Dimensionality","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2608.16760","title":"On the Principles Behind Neural Network Optimizers","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.02451","title":"Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}