{"total":383,"rows":[{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"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":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","cited_by_count":77,"area":null},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"area":null},{"id":"2210.09054","title":"On the Identifiability and Estimation of Causal Location-Scale Noise Models","created":"2022-10-13","cited_by_count":56,"area":null},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2106.08085","title":"Natural continual learning: success is a journey, not (just) a destination","created":"2021-06-15","cited_by_count":46,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2103.01133","title":"Posterior Meta-Replay for Continual Learning","created":"2021-03-01","cited_by_count":45,"area":null},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2102.05375","title":"Strength of Minibatch Noise in SGD","created":"2021-02-10","cited_by_count":39,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2402.03917","title":"Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning","created":"2024-02-06","cited_by_count":37,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2106.02305","title":"Local Adaptivity in Federated Learning: Convergence and Consistency","created":"2021-06-04","cited_by_count":31,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"area":null},{"id":"2204.12965","title":"Particle algorithms for maximum likelihood training of latent variable models","created":"2022-04-27","cited_by_count":26,"area":null},{"id":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"area":null},{"id":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","cited_by_count":24,"area":null},{"id":"2211.14133","title":"PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2106.05367","title":"Pulling back information geometry","created":"2021-06-09","cited_by_count":23,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2310.06131","title":"Learning Layer-wise Equivariances Automatically using Gradients","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"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":"2107.04205","title":"On the Variance of the Fisher Information for Deep Learning","created":"2021-07-09","cited_by_count":22,"area":null},{"id":"2206.08478","title":"Classification of datasets with imputed missing values: does imputation quality matter?","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2103.08933","title":"Reweighting Augmented Samples by Minimizing the Maximal Expected Loss","created":"2021-03-16","cited_by_count":21,"area":null},{"id":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"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":"2106.08769","title":"Knowledge-Adaptation Priors","created":"2021-06-16","cited_by_count":20,"area":null},{"id":"2310.03597","title":"Sampling via Gradient Flows in the Space of Probability Measures","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2402.07114","title":"Towards Quantifying the Preconditioning Effect of Adam","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2503.18595","title":"Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition","created":"2025-03-24","cited_by_count":19,"area":null},{"id":"2211.01642","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2302.12565","title":"Variational Linearized Laplace Approximation for Bayesian Deep Learning","created":"2023-02-24","cited_by_count":18,"area":null},{"id":"2405.16350","title":"A Second-Order Perspective on Model Compositionality and Incremental Learning","created":"2024-05-25","cited_by_count":18,"area":null},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2106.12506","title":"Sampling with Mirrored Stein Operators","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2510.09378","title":"The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton","created":"2025-10-10","cited_by_count":17,"area":null},{"id":"2106.02624","title":"ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2207.08988","title":"Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices","created":"2022-07-18","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":"2209.10888","title":"Amortized Variational Inference: A Systematic Review","created":"2022-09-22","cited_by_count":16,"area":null},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2302.11024","title":"Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance","created":"2023-02-21","cited_by_count":16,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2403.12329","title":"FedFisher: Leveraging Fisher Information for One-Shot Federated Learning","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2406.06420","title":"An Improved Empirical Fisher Approximation for Natural Gradient Descent","created":"2024-06-10","cited_by_count":15,"area":null},{"id":"2203.01097","title":"Model-agnostic out-of-distribution detection using combined statistical tests","created":"2022-03-02","cited_by_count":14,"area":null},{"id":"2307.04526","title":"Self-Expanding Neural Networks","created":"2023-07-10","cited_by_count":14,"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":"2405.19681","title":"Bayesian Online Natural Gradient (BONG)","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2405.06275","title":"Pruning as a Domain-specific LLM Extractor","created":"2024-05-10","cited_by_count":13,"area":null},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2407.15693","title":"Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2502.11756","title":"On the Computation of the Fisher Information in Continual Learning","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2203.10736","title":"The activity-weight duality in feed forward neural networks: The geometric determinants of generalization","created":"2022-03-21","cited_by_count":12,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"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":"2406.05072","title":"Linearization Turns Neural Operators into Function-Valued Gaussian Processes","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2109.14158","title":"Second-Order Neural ODE Optimizer","created":"2021-09-29","cited_by_count":11,"area":null},{"id":"2206.15273","title":"Invariance Properties of the Natural Gradient in Overparametrised Systems","created":"2022-06-30","cited_by_count":11,"area":null},{"id":"2407.13711","title":"FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2601.21750","title":"FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2103.01327","title":"A practical tutorial on Variational Bayes","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2110.07567","title":"Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2302.13163","title":"Achieving High Accuracy with PINNs via Energy Natural Gradients","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2304.08309","title":"Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization","created":"2023-04-17","cited_by_count":10,"area":null},{"id":"2306.03968","title":"Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels","created":"2023-06-06","cited_by_count":10,"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":"2409.17357","title":"Revisiting inverse Hessian vector products for calculating influence functions","created":"2024-09-25","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2104.13289","title":"Model-centric Data Manifold: the Data Through the Eyes of the Model","created":"2021-04-26","cited_by_count":9,"area":null},{"id":"2201.10285","title":"Efficient Approximations of the Fisher Matrix in Neural Networks using Kronecker Product Singular Value Decomposition","created":"2022-01-25","cited_by_count":9,"area":null},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"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":"2406.17263","title":"Efficient, Multimodal, and Derivative-Free Bayesian Inference With Fisher-Rao Gradient Flows","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2410.10986","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","created":"2024-10-14","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":"2504.02666","title":"BECAME: BayEsian Continual Learning with Adaptive Model MErging","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null}],"next_cursor":"100"}