Hessian

Ask about this topic

Momentum

12 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 92

All topics
CardsList

  1. Classical Hardness of Learning Functions of Hamiltonians

    Oct 1, 2026Sota Hashimoto, Akinori KawachiQuantum LearningQuantum Machine Learning

    Graduate School of Engineering, Mie University

  2. Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin Sampling

    Sep 30, 2026Yuchen Xin, Zhihua ZhangLangevin DynamicsLipschitz Continuity

    School of Mathematical Sciences, Peking University

  3. Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD

    Sep 30, 2026Junghoon SeoStochastic Gradient DescentGaussian Primitives

    PIT IN Corp., South Korea

  4. A Generalisation Signal Need Not Be a Model-Selection Signal

    Sep 30, 2026Aditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar +5Model SelectionSpearman Correlation

    Department of CS&IS, BITS Pilani, K K Birla Goa Campus · LexisNexis Legal & Professional · Center for AI and Supercomputing, Mahindra University

  5. Deep kernel hedging

    Sep 28, 2026Jean-Loup Dupret, Donatien Hainaut, Edouard MotteHessianEmpirical Risk Minimization

    University of Amsterdam, Amsterdam School of Economics · ETH Zurich, Department of Mathematics, RiskLab · Université Catholique de Louvain, LIDAM–ISBA

  6. The Composition Gap in Dataset Distillation

    Sep 28, 2026Guang Li, Takahiro Ogawa, Miki HaseyamaDiffusion-Based Dataset DistillationProbe-Logit Distillation

    Hokkaido University

  7. Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement

    Sep 22, 2026Akihiro Yoshida, Yuma IchikawaMixed-Precision QuantizationLarge Language Model Quantization

    Fujitsu Limited, Institute of Science Tokyo · Fujitsu Limited, RIKEN Center for AIP

  8. Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models

    Sep 21, 2026Zijian Li, Ruichu Cai, Feng Xie +7HessianLatent Variable

    Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Carnegie Mellon University, Pittsburgh, PA, USA · Guangdong University of Technology, Guangzhou, China +3

  9. LiLi: Lie Theory Based 3D LiDAR Scan Alignment Degeneracy Detection

    Sep 15, 2026Vsevolod Hulchuk, Jan Bayer, Jan FaiglHomographyLie Group

    Faculty of Electrical Engineering, Czech Technical University, Technická 2, 166 27, Prague, Czech Republic

  10. Optimization over covariance matrices with a parameterized metric

    Sep 15, 2026Yibang Li, Bamdev Mishra, Pratik Jawanpuria +1Riemannian OptimizationHessian

    Nanyang Technological University, Singapore · Microsoft India · Indian Institute of Technology Bombay, India

  11. Federated stochastic bilevel optimization with fully first-order gradients

    Sep 14, 2026Yihan Zhang, Rohit Dhaipule, Chiu C Tan +2Bilevel OptimizationGradient Descent

    1Temple University · 2Stony Brook University

  12. Correlation-Guided Fast Machine Unlearning via Hessian Analysis

    Sep 14, 2026Ayushi Thakur, Ruchir Gupta, Amit Kumar Jaiswal +1Machine UnlearningPrivacy-Preserving Machine Learning

    Department of Computer Science and Engineering, Indian Institute of Technology (Banaras Hindu University) Varanasi, India · Halmstad University, Sweden

  13. Hard-ReLU Gradient Descent Selects an Event-Free Sensitivity Limit

    Aug 31, 2026Xiaoyang Li, Runni ZhouGradientLocal Curvature

    College of Medicine and Biological Information Engineering Northeastern University, Shenyang, China

  14. Functional Degeneracy in Neural Networks: Measurement and Pruning

    Aug 31, 2026Maria Matveev, Pascal Esser, Ayush Bharadwaj +2Unstructured PruningNeural Network

    Department of Mathematics, LMU Munich · Munich Center for Machine Learning (MCML) · Independent +3

  15. Estimating Population-Risk Curves Along Nonconvex Gradient Flows from the Training Sample

    Aug 31, 2026Mingzhi SongWasserstein Gradient FlowsGradient

    Department of Mathematics, The University of Hong Kong

  16. Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks

    Aug 28, 2026Munawar Hasan, Apostol VassilevFeed-ForwardTransformer Architectures

    National Institute of Standards and Technology, USA · Michigan Technological University, USA

  17. A Compositional Theory of Curvature in Probabilistic Circuits

    Aug 13, 2026Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay +3Sharpness-Aware MinimizationProbabilistic Model

    Mehta Family School of Data Science and Artificial Intelligence, Department of Data Science, Indian Institute of Technology Palakkad, Kerala, India · Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, Richardson, TX, USA · AT&T CDO

  18. Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level

    Aug 13, 2026Yicong Jiang, Feihu HuangBilevel OptimizationMulti-Objective Optimization

    College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China · College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China; and also with MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China

  19. HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

    Aug 12, 2026Yuefeng ZhangLearned Image CompressionGenerative Image Compression

    Beijing Institute of Computer Technology and Application, Beijing, China · School of Elite Engineering, Northwestern Polytechnical University, Shaanxi, China

  20. Efficient Hypergradient Descent for Inverse Reinforcement Learning

    Aug 11, 2026Nikita Sevriukov, Anna Barabanova, Uliana Gagarina +4Offline Reinforcement LearningReward Functions

    HSE University Moscow, Russia

  21. Exact Rank-Space KL Projection for Shared-Marginal Low-Rank Factors: Application to Doubly Stochastic Clustering

    Aug 9, 2026Enliang HuLow-Rank StructureFactor

  22. Adaptive KappaSharp: Condition-Number Shaping for Preferential Bayesian Optimization

    Aug 8, 2026Ketong Shao, Jialu Wang, Xuekai Pei +1Bayesian OptimizationHessian

    University of California, Berkeley · 2Independent · 3Wuhan University

  23. Establishing Boundary KKT Convergence of Mirror Descent through Reparameterization

    Aug 7, 2026Kuangyu Ding, Kim-Chuan TohMirror DescentConvergence

    School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA. · Department of Mathematics, National University of Singapore, Singapore 119076.

  24. Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks

    Aug 6, 2026Björn Ladewig, Ibrahim Talha Ersoy, Karoline WiesnerFeature LearningAnisotropic Loss Landscapes

    Institute of Physics and Astronomy, University of Potsdam

  25. BaKron: Efficient Quantization with Kronecker-Factored Hessians

    Aug 6, 2026Johann Birnick, Rayan SaabHessianMatrix Multiplication

    Department of Mathematics · University of California San Diego · La Jolla, California, United States +1

  26. On the Implicit Flatness Bias of Sharpness-Aware Minimization: A Linear Stability Analysis with Quantitative Hyperparameter Bounds

    Aug 4, 2026Jiaxin Deng, Junbiao PangSharpness-Aware MinimizationHessian

    Beijing University of Technology

  27. The Condition-Number Barrier in Sparse Least Squares

    Aug 3, 2026Honghao Lin, Vahab Mirrokni, David P. WoodruffConvex OptimizationLeast Squares

    Google Research, Carnegie Mellon University / Texas A&M University. · Google Research. · Google Research and Carnegie Mellon University.

  28. Generalized Quadratic Gradient: A New Direction in Optimization via the Fusion of Positive-Definite Curvature Matrices and Gradients into A Unified Framework

    Aug 3, 2026John ChiangHessianNewton

  29. SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation

    Jul 25, 2026Aditya Dewan, Arjun Yogeswaran, Benjamin FedorukKnowledge DistillationHessian

    Carnegie Mellon University · Ontario Tech University

  30. \k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating

    Jul 24, 2026Jianghui Wang, Silong Yong, Francesco Orabona +3Multi-LoraLow-Rank Structure

    King Abdullah University of Science and Technology · Carnegie Mellon University

  31. A Defense of the Quadratic Model

    Jul 23, 2026Alexandru Meterez, Pranav Ajit Nair, Depen Morwani +3Anisotropic Loss LandscapesLarge Language Model Training

    1Kempner Institute at Harvard University · †: Work done while at Harvard. · 2MIT

  32. How the Hessian-Spectrum of Neural Networks Depends on Data

    Jul 15, 2026Jasraj Singh, Enea Monzio Compagnoni, Antonio OrvietoHessianTwo-Layer Neural Networks

    ELLIS Institute, Tübingen, Germany · Universität Basel, Basel, Switzerland · MPI-IS, Tübingen, Germany

  33. Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima

    Jul 9, 2026Lachlan Ewen MacDonald, René VidalGradient DescentHessian

    Innovation in Data Engineering and Science (IDEAS) · University of Pennsylvania Pennsylvania, PA 19104

  34. KronQ: LLM Quantization via Kronecker-Factored Hessian

    Jul 8, 2026Donghyun Lee, Yuhang Li, Ruokai Yin +1Large Language Model QuantizationPost-Training Quantization

    University of Southern California · Yale University

  35. Explaining Near-Zero Hessian Eigenvalues Through Approximate Symmetries in Neural Networks

    Jul 8, 2026Marcel Kühn, Bernd RosenowHessianAnisotropic Loss Landscapes

    Institut für Theoretische Physik, Universität Leipzig, 04103 Leipzig, Germany · ScaDS.AI Dresden/Leipzig, Universität Leipzig, 04105 Leipzig, Germany

  36. Restricted Dynamic Geometric Complexity: Path-Space Reduction and Möbius--Jacobi Response

    Jul 8, 2026Zavier LiSpectral PreconditioningShape Optimization

    Xidian University, Xi’an, China

  37. On the Condition Number Upper Bound of the L-BFGS Inverse Hessian Approximation Matrix with a Two-Sided Geometric Envelope Safeguarding Mechanism

    Jul 7, 2026Don LiHessianNewton

    Department of Mathematics & Statistics Portland State University Portland, OR 97201, USA

  38. Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam

    Jul 4, 2026Ashmitha R, Jörg FrochteAdamSharpness-Aware Minimization

    Department of Artificial Intelligence and Data Science, Sri Ramakrishna Engineering College, Anna University, Coimbatore 641022, Tamil Nadu, India · Interdisciplinary Institute for Applied AI and Data Science Ruhr (AKIS), Department of Electrical Engineering and Computer Science, Bochum University of Applied Sciences, Am Hochschulcampus 1, 44801 Bochum, Germany

  39. GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics

    Jul 1, 2026Jeffrey Fang, Keyi Shen, Anutam Srinivasan +1Nonlinear DynamicsNeural Dynamics

  40. Why can genetic algorithms work in high-dimensional search spaces?

    Jun 29, 2026Stephen WhitelamGenetic AlgorithmsGradient Descent

    Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USA

  41. Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules

    Jun 29, 2026Muhammad Hamza, Ayush GoelStochastic Gradient DescentHessian

    Indian Institute of Technology Kharagpur · Indian Institute of Technology Kharagpur (IIT KGP)

  42. Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization

    Jun 29, 2026Marcelina Marjankowska, Valerio Modugno, Paolo BaruccaHessianLocal Curvature

    Financial Computing and Analytics Group, University College London · Robot Perception and Learning Lab, University College London

  43. Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks

    Jun 27, 2026Yuto Omae, Kazuki Sakai, Yohei Kakimoto +3HessianGradient Descent

    Nihon University (Japan) · National Institute of Technology, Nagaoka College (Japan) · Tokyo City University (Japan)

  44. The Degeneracy Distillery

    Jun 22, 2026T. Lucas Makinen, Deaglan J. Bartlett, Niall Jeffrey +1Fisher Information MatrixHessian

    Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Wilberforce Rd, Cambridge CB3 0WA, United Kingdom · Imperial Centre for Inference and Cosmology (ICIC), Imperial College London, Prince Consort Road, London SW7 2AZ, United Kingdom · Astrophysics, University of Oxford, Oxford OX1 3RH, United Kingdom +5

  45. Hessian-augmented Supervised Learning for Hamilton-Jacobi-Bellman PDEs

    Jun 22, 2026Matías Gómez-Aedo, Behzad Azmi, Yuyang Huang +2Optimal ControlHamilton-Jacobi Reachability

    Department of Mathematics, Imperial College London, South Kensington Campus, SW7 2AZ London, UK · Department of Mathematics and Statistics, University of Konstanz, Germany · RICAM and Institute of Mathematics and Scientific Computing, University of Graz, Austria

  46. Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design

    Jun 19, 2026Junren Chen, Arya MazumdarLogistic RegressionFinite-Sample

    Department of Mathematics, University of Maryland, College Park. · Halıcıoğlu Data Science Institute, UC San Diego.

  47. Interactive Pareto navigation for deep multi-task learning

    Jun 17, 2026Augustina C. Amakor, Konstantin Sonntag, Sebastian PeitzPareto FrontierMulti-Objective Reinforcement Learning

    Department of Computer Science, TU Dortmund, Dortmund, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence

  48. BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

    Jun 17, 2026Jiaxing Wang, Deping Xiang, Jin Xu +9Alignment-Aware SelectionLarge Language Model Training

  49. Taming Curvature: Architecture Warm-Up for Stable Transformer Training

    Jun 15, 2026Sameera Ramasinghe, Ajanthan Thalaiyasingam, Hadi Mohaghegh Dolatabadi +6Curvature-Aware Spectral FrameworkTransformer Architectures

    Pluralis Research

  50. Accelerating SAV-based optimization via randomized low-rank Hessian approximation

    Jun 9, 2026Ryo Sagawa, Daisuke Furihata, Yuto MiyatakeHessianNewton

    Department of Pure and Applied Mathematics, Graduate School of Information Science and Technology, The University of Osaka · D3 Center, The University of Osaka

  51. Neural Legendre-Fenchel transform with Hessian Preconditioning

    Jun 8, 2026Basile Plus-Gourdon, Frank NielsenSpectral PreconditioningHessian

    ´Ecole Normale Sup´erieure · Paris-Saclay, France · Sony Computer Science Laboratories Inc. +1

  52. REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance

    Jun 8, 2026Zhang Chen, Shuai Wan, Mengting Yu +2Dynamic 3D Gaussian Splatting3D Gaussian

    School of Electronics and Information, Northwestern Polytechnical University · School of Telecommunication Engineering, Xidian University · Department of Computer Science, City University of Hong Kong

  53. Sharp First-Order Lower Bounds for Higher-Order Smooth Nonconvex Optimization

    Jun 3, 2026Dongruo ZhouStochastic Convex OptimizationFirst Order Oracle Complexity

    Department of Computer Science, Indiana University Bloomington, IN 47408, USA

  54. A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks

    Jun 3, 2026Tian Ding, Dawei Li, Ruoyu SunTwo-Layer Neural NetworksAnisotropic Loss Landscapes

    Shenzhen International Center of Industrial and Applied Mathematics, Shenzhen Research Institute of Big Data, China; Shenzhen Loop Area Institute, China; AutoKernel, China. · Shenzhen Loop Area Institute, China · AutoKernel, China +3

  55. Edge of Stability Selectively Shapes Learning Across the Data Distribution

    Jun 2, 2026Shauna Kwag, Anakha Ganesh, Tomaso Poggio +1HessianDistributions

    MIT

  56. Learning Chaotic Dynamics through Second-Order Geometric Supervision

    Jun 1, 2026Shinhoo Kang, Hai V. Nguyen, Tan Bui-ThanhChaosJacobian

    Department of Computer Science and Software Engineering, Korea University, Sejong 30019, KR · Department of Aerospace Engineering and Engineering Mechanics, The Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, 2026 TX, USA

  57. Rethinking Bregman Divergences in Kronecker-Factored Optimizers

    May 30, 2026Bing Liu, Wenjie Zhou, Chengcheng ZhaoSpectral PreconditioningBregman Divergences

    College of Control Science and Engineering, Zhejiang University · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences

  58. Exploiting weight-space symmetries for approximating curvature

    May 30, 2026Artem Artemev, Rui Xia, Benjamin M. Boyd +4Local CurvatureHessian

    MediaTek, Cambridge, UK · University of Cambridge, Cambridge, UK · Vector Institute, Toronto, Canada

  59. Improved Guarantees for Langevin Monte Carlo with Average Smoothness

    May 29, 2026Arnak S. Dalalyan, Avetik KaragulyanLangevin DynamicsLog-Concave Distributions

    CREST, ENSAE Paris, Institut Polytechnique de Paris and MBZUAI · L2S, CNRS, Centrale Supélec, Université Paris-Saclay

  60. Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens

    May 29, 2026Junbin Qiu, Zhaowei Hong, Renzhe Xu +1HessianZeroth-Order

    Hong Kong University of Science and Technology (Guangzhou) · Shanghai University of Finance and Economics