Image de couverture de livre

Hessian of Perplexity for Large Language Models by PyTorch autograd (Open Source)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Ilin, Ivan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language 68T07, 65K10, 65Y05
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A resource-efficient model for deep kernel learning
par: D'Amore, Luisa
Publié: (2024)

Hybrid Least Squares/Gradient Descent Methods for DeepONets
par: Choi, Jun, et autres
Publié: (2025)

Bare-Metal Tensor Virtualization: Overcoming the Memory Wall in Edge-AI Inference on ARM64
par: Kilictas, Bugra, et autres
Publié: (2026)

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
par: Antil, Harbir, et autres
Publié: (2025)

Layer-Parallel Training for Transformers
par: Jiang, Shuai, et autres
Publié: (2026)

A Low-complexity Structured Neural Network to Realize States of Dynamical Systems
par: Aluvihare, Hansaka, et autres
Publié: (2025)

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
par: Alberti, Giovanni S., et autres
Publié: (2025)

Multilevel Training for Kolmogorov Arnold Networks
par: Southworth, Ben S., et autres
Publié: (2026)

Approximation of the Proximal Operator of the $\ell_\infty$ Norm Using a Neural Network
par: Linehan, Kathryn, et autres
Publié: (2024)

Recent Advances in Non-convex Smoothness Conditions and Applicability to Deep Linear Neural Networks
par: Patel, Vivak, et autres
Publié: (2024)

To be or not to be stable, that is the question: understanding neural networks for inverse problems
par: Evangelista, Davide, et autres
Publié: (2022)

Space-time parallel scaling of Parareal with a physics-informed Fourier Neural Operator coarse propagator applied to the Black-Scholes equation
par: Ibrahim, Abdul Qadir, et autres
Publié: (2024)

Randomized Forward Mode of Automatic Differentiation For Optimization Algorithms
par: Shukla, Khemraj, et autres
Publié: (2023)

Learning Nonlinear Finite Element Solution Operators using Multilayer Perceptrons and Energy Minimization
par: Larson, Mats G., et autres
Publié: (2024)

A network based approach for unbalanced optimal transport on surfaces
par: Pan, Jiangong, et autres
Publié: (2024)

Approximation and Gradient Descent Training with Neural Networks
par: Welper, G.
Publié: (2024)

Neural-network methods for two-dimensional finite-source reflector design
par: Hacking, Roel, et autres
Publié: (2026)

RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
par: Gattiglio, Guglielmo, et autres
Publié: (2024)

Objective Value Change and Shape-Based Accelerated Optimization for the Neural Network Approximation
par: Xie, Pengcheng, et autres
Publié: (2025)

Progressive Power Homotopy for Non-convex Optimization
par: Xu, Chen
Publié: (2026)

Kourkoutas-Beta: A Sunspike-Driven Adam Optimizer with Desert Flair
par: Kassinos, Stavros C.
Publié: (2025)

Neural Preconditioning via Krylov Subspace Geometry
par: Dimola, Nunzio, et autres
Publié: (2025)

The Pontryagin Maximum Principle for Training Convolutional Neural Networks
par: Hofmann, Sebastian, et autres
Publié: (2025)

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures
par: Bolshim, Maxim, et autres
Publié: (2026)

Local properties of neural networks through the lens of layer-wise Hessians
par: Bolshim, Maxim, et autres
Publié: (2025)

Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training
par: Bolshim, Maxim, et autres
Publié: (2026)

Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization
par: Yao, Boyuan, et autres
Publié: (2025)

High-performance matrix-free unfitted finite element operator evaluation
par: Bergbauer, Maximilian, et autres
Publié: (2024)

Matrix-Free Evaluation of High-Order Shifted Boundary Finite Element Operators
par: Wichrowski, Michał
Publié: (2025)

Polyharmonic Cascade
par: Bakhvalov, Yuriy N.
Publié: (2025)

SplInterp: Improving our Understanding and Training of Sparse Autoencoders
par: Budd, Jeremy, et autres
Publié: (2025)

PETScML: Second-order solvers for training regression problems in Scientific Machine Learning
par: Zampini, Stefano, et autres
Publié: (2024)

A Judge Agent Closes the Reliability Gap in AI-Generated Scientific Simulation
par: Yang, Chengshuai
Publié: (2026)

Sequential Least-Squares Estimators with Fast Randomized Sketching for Linear Statistical Models
par: Chen, Guan-Yu, et autres
Publié: (2025)

Improving Matrix Exponential for Generative AI Flows: A Taylor-Based Approach Beyond Paterson--Stockmeyer
par: Sastre, Jorge, et autres
Publié: (2025)

A Neumann-Neumann Acceleration with Coarse Space for Domain Decomposition of Extreme Learning Machines
par: Lee, Chang-Ock, et autres
Publié: (2025)

Parallel-in-time Multilevel Krylov Methods: A Prototype
par: Erlangga, Yogi A.
Publié: (2023)

Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising
par: Gruber, Nadja, et autres
Publié: (2023)

Neural Network-Based Parameter Estimation for Non-Autonomous Differential Equations with Discontinuous Signals
par: Jo, Hyeontae, et autres
Publié: (2025)

SDFs from Unoriented Point Clouds using Neural Variational Heat Distances
par: Weidemaier, Samuel, et autres
Publié: (2025)