conftrace_

hessian matrix

33 papers

Explore in graph

Co-occurring keywords

neural network optimization (1293) gradient descent (1144) second-order optimization (93) stochastic gradient descent (1091) convergence rate (607) hessian eigenvalue (26) newton method (64) optimization landscape (39) adaptive algorithm (114) relu network (143)

Papers

First-Order Error Matters: Accurate Compensation for Quantized Large Language Models AAAI 2026
Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models EMNLP 2025
Asymmetric Learning for Spectral Graph Neural Networks AAAI 2025
Boosting Adversarial Transferability via Negative Hessian Trace Regularization ICCV 2025
The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank AAAI 2024
Clarifying the Behavior and the Difficulty of Adversarial Training AAAI 2024
Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport NIPS 2024
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms NIPS 2024
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024
The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023
Learning to Generalize Provably in Learning to Optimize AISTATS 2023
MoPe: Model Perturbation based Privacy Attacks on Language Models EMNLP 2023
Aligning Gradient and Hessian for Neural Signed Distance Function NIPS 2023
Efficient Second-Order Plane Adjustment CVPR 2023
The alignment property of SGD noise and how it helps select flat minima: A stability analysis NIPS 2022
Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 2022
Batch Normalization Preconditioning for Neural Network Training JMLR 2022
A Two-Level Decomposition Framework Exploiting First and Second Order Information for SVM Training Problems JMLR 2021
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update NIPS 2021
Analytic Insights into Structure and Rank of Neural Network Hessian Maps NIPS 2021
Non-PSD matrix sketching with applications to regression and optimization UAI 2021
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry NIPS 2020
On the interplay between noise and curvature and its effect on optimization and generalization AISTATS 2020
On the linearity of large non-linear models: when and why the tangent kernel is constant NIPS 2020