{"total":24,"rows":[{"id":"2107.04205","title":"On the Variance of the Fisher Information for Deep Learning","created":"2021-07-09","cited_by_count":22,"area":null},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2307.00908","title":"Quantum Machine Learning on Near-Term Quantum Devices: Current State of Supervised and Unsupervised Techniques for Real-World Applications","created":"2023-07-03","cited_by_count":14,"area":null},{"id":"2202.00755","title":"Lagrangian Manifold Monte Carlo on Monge Patches","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2402.05379","title":"Trade-Offs of Diagonal Fisher Information Matrix Estimators","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2202.04124","title":"A Mini-Block Fisher Method for Deep Neural Networks","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2405.18874","title":"Are queries and keys always relevant? A case study on Transformer wave functions","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2111.15256","title":"Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2502.01739","title":"Grokking vs. Learning: Same Features, Different Encodings","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2510.01240","title":"RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.15542","title":"SpikeFit: Towards Optimal Deployment of Spiking Networks on Neuromorphic Hardware","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2512.22247","title":"The Affine Divergence: Aligning Activation Updates Beyond Normalisation","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2510.06685","title":"Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2601.03162","title":"On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2603.29466","title":"An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2607.18574","title":"Conditioned Direct Feedback Alignment via Activity and Error Geometry","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2210.05268","title":"Component-Wise Natural Gradient Descent -- An Efficient Neural Network Optimization","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2505.18313","title":"PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.17488","title":"Optimizing Multi-Modality Trackers via Significance-Regularized Tuning","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2509.24728","title":"Beyond Softmax: A Natural Parameterization for Categorical Random Variables","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.06945","title":"Fisher Information, Training and Bias in Fourier Regression Models","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.13506","title":"Learning under Distributional Drift: Prequential Reproducibility as an Intrinsic Statistical Resource","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.02438","title":"Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2604.14702","title":"Gating Enables Curvature: A Geometric Expressivity Gap in Attention","created":"2026-04-16","cited_by_count":0,"area":null}],"next_cursor":null}