hessian matrix

First-Order Error Matters: Accurate Compensation for Quantized Large Language Models AAAI 2026 Associative memory and dead neurons ICLR 2025 Asymmetric Learning for Spectral Graph Neural Networks AAAI 2025 Boosting Adversarial Transferability via Negative Hessian Trace Regularization ICCV 2025 Gradient descent with generalized Newton’s method ICLR 2025 Model Immunization from a Condition Number Perspective ICML 2025 Optimal Brain Apoptosis ICLR 2025 Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models EMNLP 2025 Clarifying the Behavior and the Difficulty of Adversarial Training AAAI 2024 High-dimensional SGD aligns with emerging outlier eigenspaces ICLR 2024 Improving Computational Complexity in Statistical Models with Local Curvature Information ICML 2024 Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024 Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms NeurIPS 2024 Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport NeurIPS 2024 The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank AAAI 2024 Aligning Gradient and Hessian for Neural Signed Distance Function NeurIPS 2023 Efficient Second-Order Plane Adjustment CVPR 2023 Learning to Generalize Provably in Learning to Optimize AISTATS 2023 MoPe: Model Perturbation based Privacy Attacks on Language Models EMNLP 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 Batch Normalization Preconditioning for Neural Network Training JMLR 2022 Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022 Analytic Insights into Structure and Rank of Neural Network Hessian Maps NeurIPS 2021