{"total":43,"rows":[{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"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":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"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":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"area":null},{"id":"2302.03764","title":"Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions","created":"2023-02-07","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":"2404.04002","title":"Continual Learning with Weight Interpolation","created":"2024-04-05","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":"2401.10809","title":"Neglected Hessian component explains mysteries in Sharpness regularization","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2405.14402","title":"Exact Gauss-Newton Optimization for Training Deep Neural Networks","created":"2024-05-23","cited_by_count":10,"area":null},{"id":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","cited_by_count":9,"area":null},{"id":"2511.07971","title":"Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning","created":"2025-11-11","cited_by_count":7,"area":null},{"id":"2208.05924","title":"Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2205.12372","title":"TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models","created":"2022-05-24","cited_by_count":3,"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":"2505.17998","title":"TRACE for Tracking the Emergence of Semantic Representations in Transformers","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2506.07661","title":"Information-Theoretic Framework for Understanding Modern Machine-Learning","created":"2025-06-09","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":"2307.02337","title":"FAM: Relative Flatness Aware Minimization","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2509.22938","title":"Understanding SOAP from the Perspective of Gradient Whitening","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2402.03295","title":"Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2404.19725","title":"CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographics","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2405.12493","title":"Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2501.06954","title":"A Hessian-informed hyperparameter optimization for differential learning rate","created":"2025-01-12","cited_by_count":1,"area":null},{"id":"2504.14701","title":"Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2510.07758","title":"R\\'enyi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2512.08314","title":"Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2601.18420","title":"Gradient Regularized Natural Gradients","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2601.21626","title":"HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.10202","title":"Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2204.04348","title":"Neuronal diversity can improve machine learning for physics and beyond","created":"2022-04-09","cited_by_count":0,"area":null},{"id":"2410.10690","title":"Dynamical loss functions shape landscape topography and improve learning in artificial neural networks","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2510.02174","title":"Flatness-Aware Stochastic Gradient Langevin Dynamics","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2512.13416","title":"Learning to Generate Cross-Task Unexploitable Examples","created":"2025-12-15","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":"2606.02078","title":"Beyond $\\ell_2$-norm and $\\ell_\\infty$-norm: A Curvature-Inspired $\\ell_p$-Norm Scheme for Deep Neural Networks","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.28662","title":"Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks","created":"2026-06-27","cited_by_count":0,"area":null}],"next_cursor":null}