{"total":32,"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":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2304.09871","title":"A Theory on Adam Instability in Large-Scale Machine Learning","created":"2023-04-19","cited_by_count":56,"area":null},{"id":"2303.01372","title":"High-dimensional analysis of double descent for linear regression with random projections","created":"2023-03-02","cited_by_count":47,"area":null},{"id":"2502.15588","title":"Improving the Scaling Laws of Synthetic Data with Deliberate Practice","created":"2025-02-21","cited_by_count":17,"area":null},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2208.13219","title":"Visualizing high-dimensional loss landscapes with Hessian directions","created":"2022-08-28","cited_by_count":16,"area":null},{"id":"2210.12760","title":"On double-descent in uncertainty quantification in overparametrized models","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15,"area":null},{"id":"2212.02083","title":"On the Overlooked Structure of Stochastic Gradients","created":"2022-12-05","cited_by_count":13,"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":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2210.07612","title":"Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2306.14975","title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2411.15111","title":"Learnable Activation Functions in Physics-Informed Neural Networks for Solving Partial Differential Equations","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2311.07013","title":"A PAC-Bayesian Perspective on the Interpolating Information Criterion","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2411.02139","title":"Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2206.00823","title":"Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2311.01358","title":"The Universal Statistical Structure and Scaling Laws of Chaos and Turbulence","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2502.13583","title":"Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2508.20036","title":"Eigenvalue distribution of the Neural Tangent Kernel in the quadratic scaling","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.17486","title":"Local properties of neural networks through the lens of layer-wise Hessians","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2408.15784","title":"Implicit Regularization Paths of Weighted Neural Representations","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2409.11995","title":"Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2411.06770","title":"Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2502.11450","title":"What Scalable Second-Order Information Knows for Pruning at Initialization","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2405.10957","title":"Statistical Mechanics and Artificial Neural Networks: Principles, Models, and Applications","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2510.17120","title":"Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2605.06081","title":"Fast Gauss-Newton for Multiclass Cross-Entropy","created":"2026-05-07","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}],"next_cursor":null}