{"total":15,"rows":[{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2205.15142","title":"Special Properties of Gradient Descent with Large Learning Rates","created":"2022-05-30","cited_by_count":10,"area":null},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2603.09355","title":"SHANG++: Robust Stochastic Acceleration under Multiplicative Noise","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2605.26000","title":"Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2605.21292","title":"Unbiased Gradients, Moving Stability Boundaries: Exact Mini-Batch Geometry in Linear Self-Attention","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2503.02178","title":"Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2606.00293","title":"Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.03377","title":"Spectral Signatures of Large Language Models","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.16084","title":"Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.12994","title":"Dimension-Corrected Hitting Times for Heavy-Tailed Spectral Emergence in Neural Optimizer Dynamics","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19170","title":"Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.05599","title":"Gaussian Limits for SGD Without Stationary Moments","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}