{"total":58,"rows":[{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2509.10167","title":"The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram","created":"2025-09-12","cited_by_count":17,"area":null},{"id":"2510.01098","title":"Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time","created":"2025-10-01","cited_by_count":16,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2606.18524","title":"On the Residual Scaling of Looped Transformers: Stability and Transferability","created":"2026-06-16","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":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2512.22768","title":"Understanding the Mechanisms of Fast Hyperparameter Transfer","created":"2025-12-28","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":"2603.21191","title":"On the Role of Batch Size in Stochastic Conditional Gradient Methods","created":"2026-03-22","cited_by_count":7,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2605.07870","title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2604.01978","title":"Homogenized Transformers","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2510.07554","title":"Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2511.01734","title":"A Proof of Learning Rate Transfer under $\\mu$P","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2511.21377","title":"Controlling changes to attention logits","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2604.27077","title":"Learning Rate Transfer in Normalized Transformers","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.22297","title":"One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.05361","title":"MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2601.04890","title":"Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.07697","title":"On the Infinite Width and Depth Limits of Predictive Coding Networks","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.21486","title":"Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.26459","title":"MuCon: Clipped Muon Updates for LLM Training","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2606.29158","title":"On the Nonlinearity of Learning Rate Scaling for LLM Training","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2602.04396","title":"LoRDO: Distributed Low-Rank Optimization with Infrequent Communication","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.09877","title":"Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.15290","title":"GQA-{\\mu}P: The maximal parameterization update for grouped query attention","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.06418","title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","created":"2026-06-04","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":"2609.03589","title":"Correlated initialization of deep residual networks","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2602.20937","title":"Extending $\\mu$P: Spectral Conditions for Feature Learning Across Optimizers","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.09154","title":"Predicting Large Model Test Losses with a Noisy Quadratic System","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.13405","title":"When is Warmstarting Effective for Scaling Language Models?","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.27989","title":"The Model Shape Behind Scaling Laws: A Gradient Superposition Perspective","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.28975","title":"A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.07884","title":"Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2609.30633","title":"Stable initialization without the CLT","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.06784","title":"How to scale your HEP ML models: A recipe for robust architecture comparisons at scale","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14344","title":"On the Depth Transfer of Neural Optimizers via L-Smoothness","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}