{"total":144,"rows":[{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"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":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","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":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53,"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":"2103.01133","title":"Posterior Meta-Replay for Continual Learning","created":"2021-03-01","cited_by_count":45,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2312.08977","title":"Weighted Ensemble Models Are Strong Continual Learners","created":"2023-12-14","cited_by_count":42,"area":null},{"id":"2102.01936","title":"A Bayesian Federated Learning Framework with Online Laplace Approximation","created":"2021-02-03","cited_by_count":41,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"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":"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":"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":"2203.13167","title":"Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization","created":"2022-03-24","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":"2205.15704","title":"Mitigating Dataset Bias by Using Per-sample Gradient","created":"2022-05-31","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":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20,"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":"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":"2106.12772","title":"Task-agnostic Continual Learning with Hybrid Probabilistic Models","created":"2021-06-24","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":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15,"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":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2304.05187","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","created":"2023-04-11","cited_by_count":14,"area":null},{"id":"2210.06895","title":"GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization","created":"2022-10-13","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":"2402.06859","title":"LiRank: Industrial Large Scale Ranking Models at LinkedIn","created":"2024-02-10","cited_by_count":12,"area":null},{"id":"2202.03493","title":"DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning","created":"2022-02-07","cited_by_count":11,"area":null},{"id":"2208.08112","title":"DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning","created":"2022-08-17","cited_by_count":11,"area":null},{"id":"2112.11989","title":"FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation","created":"2021-12-22","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":"2402.05379","title":"Trade-Offs of Diagonal Fisher Information Matrix Estimators","created":"2024-02-08","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":"2402.12220","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2411.10696","title":"HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization","created":"2024-11-16","cited_by_count":9,"area":null},{"id":"2206.03483","title":"Few-Shot Learning by Dimensionality Reduction in Gradient Space","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2402.04924","title":"Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching","created":"2024-02-07","cited_by_count":8,"area":null},{"id":"2110.02529","title":"On the Importance of Firth Bias Reduction in Few-Shot Classification","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2202.06236","title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","created":"2022-02-13","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":"2407.09047","title":"Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2505.18230","title":"Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models","created":"2025-05-23","cited_by_count":7,"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":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","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":"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":"2111.11542","title":"Depth Without the Magic: Inductive Bias of Natural Gradient Descent","created":"2021-11-22","cited_by_count":5,"area":null},{"id":"2210.10209","title":"Exclusive Supermask Subnetwork Training for Continual Learning","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2406.16439","title":"Continual Test-Time Adaptation for Object Detection with Adaptive Monitoring and Randomized Restoration","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2502.15756","title":"Causal Covariate Shift Correction using Fisher information penalty","created":"2025-02-11","cited_by_count":5,"area":null},{"id":"2508.13898","title":"Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2111.08577","title":"Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation","created":"2021-11-16","cited_by_count":4,"area":null},{"id":"2201.11422","title":"Fast Moving Natural Evolution Strategy for High-Dimensional Problems","created":"2022-01-27","cited_by_count":4,"area":null},{"id":"2210.02719","title":"Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networks","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2403.09891","title":"Fisher Mask Nodes for Language Model Merging","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2404.10771","title":"TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision","created":"2024-04-16","cited_by_count":4,"area":null},{"id":"2601.07197","title":"Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics","created":"2026-01-12","cited_by_count":4,"area":null},{"id":"2108.03334","title":"Towards Zero-shot Language Modeling","created":"2021-08-06","cited_by_count":3,"area":null},{"id":"2112.07344","title":"SCORE: Approximating Curvature Information under Self-Concordant Regularization","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2203.10131","title":"Half-Inverse Gradients for Physical Deep Learning","created":"2022-03-18","cited_by_count":3,"area":null},{"id":"2304.05547","title":"Taxonomic Class Incremental Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2403.00625","title":"Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2404.14875","title":"Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks","created":"2024-04-23","cited_by_count":3,"area":null},{"id":"2412.14031","title":"A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2504.04050","title":"FISH-Tuning: Enhancing PEFT Methods with Fisher Information","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2509.02407","title":"Fisher information flow in artificial neural networks","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2512.10309","title":"Tracking large chemical reaction networks and rare events by neural networks","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2202.06232","title":"Generalized Tangent Kernel: A Unified Geometric Foundation for Natural Gradient and Standard Gradient","created":"2022-02-13","cited_by_count":2,"area":null},{"id":"2210.10101","title":"Optimisation & Generalisation in Networks of Neurons","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2310.04649","title":"Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2310.14963","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2408.06699","title":"Sparse Variational Student-t Processes for Heavy-tailed Modeling","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2409.16422","title":"Is All Learning (Natural) Gradient Descent?","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2502.02345","title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2503.23257","title":"FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2510.04930","title":"Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking","created":"2025-10-06","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":"2604.14010","title":"Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2605.01046","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2605.16165","title":"Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2103.07554","title":"A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training","created":"2021-03-12","cited_by_count":1,"area":null},{"id":"2108.13299","title":"Incremental Learning for Personalized Recommender Systems","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2302.04045","title":"Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2308.10554","title":"Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations","created":"2023-08-21","cited_by_count":1,"area":null},{"id":"2404.07172","title":"A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2409.15729","title":"Sequential Learning in the Dense Associative Memory","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2411.03742","title":"Adaptive Consensus Gradients Aggregation for Scaled Distributed Training","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2411.06499","title":"Mitigating covariate shift in non-colocated data with learned parameter priors","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2507.08922","title":"The Bayesian Approach to Continual Learning: An Overview","created":"2025-07-11","cited_by_count":1,"area":null}],"next_cursor":"100"}