{"total":19,"rows":[{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53,"area":null},{"id":"2202.02526","title":"LyaNet: A Lyapunov Framework for Training Neural ODEs","created":"2022-02-05","cited_by_count":44,"area":null},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41,"area":null},{"id":"2103.06219","title":"Why flatness does and does not correlate with generalization for deep neural networks","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2211.04625","title":"Soft Augmentation for Image Classification","created":"2022-11-09","cited_by_count":11,"area":null},{"id":"2205.03940","title":"Investigating Generalization by Controlling Normalized Margin","created":"2022-05-08","cited_by_count":5,"area":null},{"id":"2103.01045","title":"Computing the Information Content of Trained Neural Networks","created":"2021-03-01","cited_by_count":3,"area":null},{"id":"2210.10101","title":"Optimisation & Generalisation in Networks of Neurons","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2110.04274","title":"Kernel Interpolation as a Bayes Point Machine","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2307.07189","title":"Multiplicative update rules for accelerating deep learning training and increasing robustness","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2311.02087","title":"Design Of Rubble Analyzer Probe Using ML For Earthquake","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2312.10672","title":"Automatic Optimisation of Normalised Neural Networks","created":"2023-12-17","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2203.08174","title":"Towards understanding deep learning with the natural clustering prior","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2608.21024","title":"RODE: A Radial-Orthogonal Decoupled Engine for Optimization","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}