{"total":217,"rows":[{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"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":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"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":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"area":null},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106,"area":null},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80,"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":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"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":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"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":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42,"area":null},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","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":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"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":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35,"area":"alignment"},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33,"area":"diffusion"},{"id":"2102.12567","title":"Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks","created":"2021-02-24","cited_by_count":32,"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":"2203.02645","title":"Acceleration of Federated Learning with Alleviated Forgetting in Local Training","created":"2022-03-05","cited_by_count":29,"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":"2208.00549","title":"Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities","created":"2022-08-01","cited_by_count":28,"area":null},{"id":"2312.00246","title":"Directions of Curvature as an Explanation for Loss of Plasticity","created":"2023-11-30","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":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","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":"2310.00339","title":"FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation","created":"2023-09-30","cited_by_count":22,"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":"2210.04994","title":"Sampling-based inference for large linear models, with application to linearised Laplace","created":"2022-10-10","cited_by_count":18,"area":null},{"id":"2308.10814","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","created":"2023-08-21","cited_by_count":18,"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":"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":"2205.04878","title":"Hybrid quantum ResNet for car classification and its hyperparameter optimization","created":"2022-05-10","cited_by_count":17,"area":null},{"id":"2302.04228","title":"Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","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":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2407.19325","title":"Investigating Critical Period Effects in Language Acquisition through Neural Language Models","created":"2024-07-27","cited_by_count":16,"area":null},{"id":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2104.08604","title":"Lifelong Learning with Sketched Structural Regularization","created":"2021-04-17","cited_by_count":15,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2112.05095","title":"Provable Continual Learning via Sketched Jacobian Approximations","created":"2021-12-09","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":"2110.14163","title":"Does the Data Induce Capacity Control in Deep Learning?","created":"2021-10-27","cited_by_count":14,"area":null},{"id":"2112.04807","title":"Effective dimension of machine learning models","created":"2021-12-09","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":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","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":"2502.11756","title":"On the Computation of the Fisher Information in Continual Learning","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11,"area":null},{"id":"2302.01332","title":"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval","created":"2023-02-02","cited_by_count":10,"area":null},{"id":"2305.09088","title":"The Hessian perspective into the Nature of Convolutional Neural Networks","created":"2023-05-16","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":"2405.14402","title":"Exact Gauss-Newton Optimization for Training Deep Neural Networks","created":"2024-05-23","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":"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":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2404.02649","title":"On the Importance of Uncertainty in Decision-Making with Large Language Models","created":"2024-04-03","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":"2410.17422","title":"Multimodal LLM Guided Exploration and Active Mapping using Fisher Information","created":"2024-10-22","cited_by_count":9,"area":"mllm"},{"id":"2412.09122","title":"LVMark: Robust Watermark for Latent Video Diffusion Models","created":"2024-12-12","cited_by_count":9,"area":"diffusion"},{"id":"2412.12484","title":"Evolutionary Optimization for Designing Variational Quantum Circuits with High Model Capacity","created":"2024-12-17","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":"2202.04124","title":"A Mini-Block Fisher Method for Deep Neural Networks","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2210.11639","title":"HesScale: Scalable Computation of Hessian Diagonals","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2301.05487","title":"FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing","created":"2023-01-13","cited_by_count":8,"area":null},{"id":"2303.05101","title":"Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2502.01866","title":"Online Curvature-Aware Replay: Leveraging $\\mathbf{2^{nd}}$ Order Information for Online Continual Learning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8,"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":"2106.03947","title":"TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion","created":"2021-06-07","cited_by_count":7,"area":null},{"id":"2107.10884","title":"Structured second-order methods via natural gradient descent","created":"2021-07-22","cited_by_count":7,"area":null},{"id":"2108.02786","title":"Quantum Continual Learning Overcoming Catastrophic Forgetting","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2302.03519","title":"Efficient Parametric Approximations of Neural Network Function Space Distance","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2311.02766","title":"Riemannian Laplace Approximation with the Fisher Metric","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2302.09275","title":"Structural Neural Additive Models: Enhanced Interpretable Machine Learning","created":"2023-02-18","cited_by_count":6,"area":null},{"id":"2305.00604","title":"ISAAC Newton: Input-based Approximate Curvature for Newton's Method","created":"2023-05-01","cited_by_count":6,"area":null},{"id":"2404.08981","title":"Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification","created":"2024-04-13","cited_by_count":6,"area":null},{"id":"2410.00131","title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2410.09940","title":"Generalized Group Data Attribution","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2103.13466","title":"Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2403.00158","title":"Automated Efficient Estimation using Monte Carlo Efficient Influence Functions","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2403.06425","title":"A Differential Geometric View and Explainability of GNN on Evolving Graphs","created":"2024-03-11","cited_by_count":4,"area":null}],"next_cursor":"100"}