paper-with-me

Papers

ASDL: A Unified Interface for Gradient Preconditioning in PyTorch

2023-05-08 · Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler

Gradient preconditioning is a key technique to integrate the second-order information into gradients for improving and extending gradient-based learning algorithms. In deep learning, stochasticity, nonconvexity, and high dimensionality lead to a wide variety of gradient preconditioning methods, with implementation complexity and inconsistent performance and feasibility. We propose the Automatic Second-order Differentiation Library (ASDL), an extension library for PyTorch, which offers various implementations and a plug-and-play unified interface for gradient preconditioning. ASDL enables the study and structured comparison of a range of gradient preconditioning methods.

📄 PDF Abstract BibTeX arXiv:2305.04684

Code (2)

kazukiosawa/asdl 공식 구현 pytorch
kazukiosawa/asdfghjkl pytorch

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Preconditioning for Accelerated Gradient Descent Optimization and Regularization

2024-09-30 · Qiang Ye

Accelerated training algorithms, such as adaptive learning rates and various normalization methods, are widely used but not fully understood. When regularization is introduced, standard optimizers like adaptive learning …

FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers

2026-07-20 · Peiyu Zang, Bosen Xie, Ruoxiang Xu, Yongqiang Cai arxiv

Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differentiation memory overhead and inefficient ex…

tntorch: Tensor Network Learning with PyTorch

2022-06-22 · Mikhail Usvyatsov, Rafael Ballester-Ripoll, Konrad Schindler

We present tntorch, a tensor learning framework that supports multiple decompositions (including Candecomp/Parafac, Tucker, and Tensor Train) under a unified interface. With our library, the user can learn and handle low…

GPUtensor algebra

Polynomial Preconditioning for Gradient Methods

2023-01-30 · Nikita Doikov, Anton Rodomanov

We study first-order methods with preconditioning for solving structured nonlinear convex optimization problems. We propose a new family of preconditioners generated by symmetric polynomials. They provide first-order opt…

PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network

2023-11-28 · Xiyuan Wang, Muhan Zhang

We introduce PyTorch Geometric High Order (PyGHO), a library for High Order Graph Neural Networks (HOGNNs) that extends PyTorch Geometric (PyG). Unlike ordinary Message Passing Neural Networks (MPNNs) that exchange messa…

Graph Neural Network