{"total":38,"rows":[{"id":"2501.18965","title":"The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training","created":"2025-01-31","cited_by_count":33,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2508.07473","title":"Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications","created":"2025-08-10","cited_by_count":17,"area":null},{"id":"2411.07061","title":"General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13,"area":null},{"id":"2405.20540","title":"Fully Unconstrained Online Learning","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2603.05002","title":"Non-Euclidean Gradient Descent Operates at the Edge of Stability","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2506.06501","title":"Optimal Rates in Continual Linear Regression via Increasing Regularization","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2602.04774","title":"Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2605.19095","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2602.07145","title":"Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2406.02773","title":"Cyclic Sparse Training: Is it Enough?","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2505.24452","title":"Stepsize anything: A unified learning rate schedule for budgeted-iteration training","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.08419","title":"Online Learning-guided Learning Rate Adaptation via Gradient Alignment","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2511.04981","title":"Scaling depth capacity via zero/one-layer model expansion","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2607.27731","title":"Towards joint scaling laws with optimal batch size schedules","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2410.15819","title":"LiMTR: Time Series Motion Prediction for Diverse Road Users through Multimodal Feature Integration","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2503.09411","title":"Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2509.23052","title":"Optimization as a Dynamical System: Generative Schedules from Latent ODEs","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2602.09842","title":"Step-Size Stability in Stochastic Optimization: A Theoretical Perspective","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.28191","title":"DongYuan: An LLM-Based Framework for Integrative Chinese and Western Medicine Spleen-Stomach Disorders Diagnosis","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.06741","title":"A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.12763","title":"Adaptive Weighted Averaging","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.10959","title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.08069","title":"BrachistoneLR: A Brachistochrone-Inspired Learning-Rate Schedule and a Controlled Benchmark of Scheduling Policies","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.06070","title":"Last-Iterate Convergence Rate of Normalized Gradient Descent under H\\\"older Smoothness","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16518","title":"Asymptotic Risk of Learning-Rate Schedules for Least-Squares Regression with Discretely Distributed Features","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}