{"total":44,"rows":[{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"area":null},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2405.15603","title":"Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2405.16397","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","created":"2024-05-26","cited_by_count":14,"area":null},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2507.01649","title":"GradMetaNet: An Equivariant Architecture for Learning on Gradients","created":"2025-07-02","cited_by_count":7,"area":null},{"id":"2509.22335","title":"Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2405.13817","title":"Thermodynamic Natural Gradient Descent","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2506.07247","title":"Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2506.12965","title":"Distributional Training Data Attribution: What do Influence Functions Sample?","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2509.23437","title":"Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2509.23592","title":"Toward a Holistic Approach to Continual Model Merging","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2602.17385","title":"Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2606.19491","title":"Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2409.07925","title":"A framework for measuring the training efficiency of a neural architecture","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2410.14325","title":"Debiasing Mini-Batch Quadratics for Applications in Deep Learning","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2512.01384","title":"CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regression","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2606.21158","title":"Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity","created":"2026-06-19","cited_by_count":2,"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":"2603.29824","title":"Curvature-Guided LoRA: Matching Full Fine-Tuning in Function Space","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2606.25975","title":"Tensorion: A Tensor-Aware Generalization of the Muon Optimizer","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.14536","title":"Muse: Representation Geometry of Muon Beyond Normalized Momentum","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2608.14303","title":"Detecting Contaminated Code-Generation Prompt Batches via Influence Functions","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2404.06549","title":"Variational Stochastic Gradient Descent for Deep Neural Networks","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2505.05017","title":"Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2509.24066","title":"A Second-Order Perspective on Pruning at Initialization and Knowledge Transfer","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.26297","title":"NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.12084","title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12208","title":"Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13418","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.30813","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.07494","title":"GeoFP8: Geometry-Aware FP8 Gradient Compression for Distributed LLM Training","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.07155","title":"Mind the Approximation: Fisher-Weighted SVD Compression for ViTs","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}