{"total":194,"rows":[{"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":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2403.14123","title":"AI and Memory Wall","created":"2024-03-21","cited_by_count":92,"area":null},{"id":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65,"area":null},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58,"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":"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":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2306.01244","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"area":null},{"id":"2303.04449","title":"Loss-Curvature Matching for Dataset Selection and Condensation","created":"2023-03-08","cited_by_count":33,"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":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2507.23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention","created":"2025-07-30","cited_by_count":28,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","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":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2110.05722","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2109.11502","title":"Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming","created":"2021-09-23","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":"2109.05198","title":"Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information","created":"2021-09-11","cited_by_count":16,"area":null},{"id":"2402.04553","title":"Curvature-Informed SGD via General Purpose Lie-Group Preconditioners","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2103.03265","title":"Better SGD using Second-order Momentum","created":"2021-03-04","cited_by_count":15,"area":null},{"id":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15,"area":null},{"id":"2502.17414","title":"X-Dancer: Expressive Music to Human Dance Video Generation","created":"2025-02-24","cited_by_count":15,"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":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2406.11151","title":"Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning","created":"2024-06-17","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":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","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":"2510.21800","title":"MARS-M: When Variance Reduction Meets Matrices","created":"2025-10-20","cited_by_count":10,"area":null},{"id":"2211.04422","title":"Black Box Lie Group Preconditioners for SGD","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2306.02527","title":"Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2407.02772","title":"Gradient descent with generalized Newton's method","created":"2024-07-03","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":"2512.14366","title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2110.01543","title":"Stochastic Anderson Mixing for Nonconvex Stochastic Optimization","created":"2021-10-04","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":"2206.15143","title":"Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning","created":"2022-06-30","cited_by_count":7,"area":null},{"id":"2310.02093","title":"Stochastic Gradient Descent with Preconditioned Polyak Step-size","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2403.02418","title":"The Role of the Time-Dependent Hessian in High-Dimensional Optimization","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2109.15048","title":"Scale-invariant Learning by Physics Inversion","created":"2021-09-30","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":"2306.06098","title":"Error Feedback Can Accurately Compress Preconditioners","created":"2023-06-09","cited_by_count":6,"area":null},{"id":"2307.00012","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","created":"2023-06-21","cited_by_count":6,"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":"2112.08916","title":"GOSH: Task Scheduling Using Deep Surrogate Models in Fog Computing Environments","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2206.00285","title":"Stochastic Gradient Methods with Preconditioned Updates","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2212.03965","title":"CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2312.17369","title":"SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2402.08784","title":"Preconditioners for the Stochastic Training of Neural Fields","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2406.06655","title":"Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2408.10419","title":"Second-Order Forward-Mode Automatic Differentiation for Optimization","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2411.02139","title":"Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2504.12905","title":"Matrix-free Second-order Optimization of Gaussian Splats with Residual Sampling","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2110.05454","title":"Momentum Centering and Asynchronous Update for Adaptive Gradient Methods","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2110.08577","title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization","created":"2021-10-16","cited_by_count":4,"area":null},{"id":"2208.05924","title":"Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2210.07880","title":"Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2301.12318","title":"Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2312.01658","title":"AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2402.11858","title":"Stochastic Hessian Fittings with Lie Groups","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2403.02833","title":"SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2403.12188","title":"PETScML: Second-order solvers for training regression problems in Scientific Machine Learning","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2411.01088","title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","created":"2024-11-02","cited_by_count":4,"area":null},{"id":"2503.22211","title":"Fuzzy Cluster-Aware Contrastive Clustering for Time Series","created":"2025-03-28","cited_by_count":4,"area":null},{"id":"2601.22137","title":"PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2111.08792","title":"PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2206.08303","title":"On Scaled Methods for Saddle Point Problems","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2210.06171","title":"Learning to Optimize Quasi-Newton Methods","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2211.15596","title":"A survey of deep learning optimizers -- first and second order methods","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2305.19416","title":"KrADagrad: Kronecker Approximation-Domination Gradient Preconditioned Stochastic Optimization","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2404.17768","title":"Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization","created":"2024-04-27","cited_by_count":3,"area":null},{"id":"2407.01825","title":"Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2407.12996","title":"Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2411.01137","title":"Data movement limits to frontier model training","created":"2024-11-02","cited_by_count":3,"area":null},{"id":"2502.14096","title":"Aligned Multi Objective Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2505.07614","title":"Bant: Byzantine Antidote via Trial Function and Trust Scores","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2506.02370","title":"Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2509.08163","title":"Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2510.27153","title":"Exploring Landscapes for Better Minima along Valleys","created":"2025-10-31","cited_by_count":3,"area":null},{"id":"2109.12504","title":"AdaInject: Injection Based Adaptive Gradient Descent Optimizers for Convolutional Neural Networks","created":"2021-09-26","cited_by_count":2,"area":null},{"id":"2111.06942","title":"Predictive coding, precision and natural gradients","created":"2021-11-12","cited_by_count":2,"area":null},{"id":"2208.07658","title":"DRAGON: Decentralized Fault Tolerance in Edge Federations","created":"2022-08-16","cited_by_count":2,"area":null}],"next_cursor":"100"}