English
Related papers

Related papers: Efficient Computation of Hessian Matrices in Tenso…

200 papers

Efficiently approximating local curvature information of the loss function is a key tool for optimization and compression of deep neural networks. Yet, most existing methods to approximate second-order information have high computational or…

Machine Learning · Computer Science 2021-11-19 Elias Frantar , Eldar Kurtic , Dan Alistarh

Second-order optimization uses curvature information about the objective function, which can help in faster convergence. However, such methods typically require expensive computation of the Hessian matrix, preventing their usage in a…

Machine Learning · Computer Science 2022-11-03 Mohamed Elsayed , A. Rupam Mahmood

A new method to represent and approximate rotation matrices is introduced. The method represents approximations of a rotation matrix $Q$ with linearithmic complexity, i.e. with $\frac{1}{2}n\lg(n)$ rotations over pairs of coordinates,…

Machine Learning · Computer Science 2014-04-30 Michael Mathieu , Yann LeCun

We introduce a fast algorithm for entry-wise evaluation of the Gauss-Newton Hessian (GNH) matrix for the fully-connected feed-forward neural network. The algorithm has a precomputation step and a sampling step. While it generally requires…

Numerical Analysis · Mathematics 2020-11-17 Chao Chen , Severin Reiz , Chenhan Yu , Hans-Joachim Bungartz , George Biros

Computing multivariate derivatives of matrix-like expressions in the compact, coordinate free fashion is very important for both theory and applied computations (e.g. optimization and machine learning). The critical components of such…

Symbolic Computation · Computer Science 2019-12-02 Maciej Skorski

When training large models, such as neural networks, the full derivatives of order 2 and beyond are usually inaccessible, due to their computational cost. Therefore, among the second-order optimization methods, it is common to bypass the…

Machine Learning · Computer Science 2025-10-01 Pierre Wolinski

The Hilbert-space Gaussian Process (HGP) approach offers a hyperparameter-independent basis function approximation for speeding up Gaussian Process (GP) inference by projecting the GP onto M basis functions. These properties result in a…

Machine Learning · Computer Science 2024-08-06 Frida Viset , Anton Kullberg , Frederiek Wesel , Arno Solin

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of…

Machine Learning · Computer Science 2020-10-08 Sören Laue , Matthias Mitterreiter , Joachim Giesen

This work presents a novel matrix-based method for constructing an approximation Hessian using only function evaluations. The method requires less computational power than interpolation-based methods and is easy to implement in matrix-based…

Numerical Analysis · Mathematics 2023-04-07 W. Hare , G. Jarry-Bolduc , C. Planiden

For minimization problems without 2nd derivative information, methods that estimate Hessian matrices can be very effective. However, conventional techniques generate dense matrices that are prohibitive for large problems. Limited-memory…

Optimization and Control · Mathematics 2025-01-22 Johannes J. Brust

Scalable algorithms to solve optimization and regression tasks even approximately, are needed to work with large datasets. In this paper we study efficient techniques from matrix sketching to solve a variety of convex constrained regression…

Machine Learning · Computer Science 2019-11-01 Graham Cormode , Charlie Dickens

Machine Learning applications on HPC systems have been gaining popularity in recent years. The upcoming large scale systems will offer tremendous parallelism for training through GPUs. However, another heavy aspect of Machine Learning is…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-07-05 Steven W. D. Chien , Artur Podobas , Ivy B. Peng , Stefano Markidis

We present an efficient algorithm for recent generalizations of optimal mass transport theory to matrix-valued and vector-valued densities. These generalizations lead to several applications including diffusion tensor imaging, color images…

Numerical Analysis · Computer Science 2017-06-28 Yongxin Chen , Eldad Haber , Kaoru Yamamoto , Tryphon T. Georgiou , Allen Tannenbaum

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective…

Machine Learning · Computer Science 2019-01-10 Tianqi Chen , Lianmin Zheng , Eddie Yan , Ziheng Jiang , Thierry Moreau , Luis Ceze , Carlos Guestrin , Arvind Krishnamurthy

In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In our method, we construct on each iteration a Krylov subspace…

Machine Learning · Statistics 2011-11-21 Oriol Vinyals , Daniel Povey

We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to…

Machine Learning · Computer Science 2020-02-11 Aditya Paliwal , Felix Gimeno , Vinod Nair , Yujia Li , Miles Lubin , Pushmeet Kohli , Oriol Vinyals

We present PYHESSIAN, a new scalable framework that enables fast computation of Hessian (i.e., second-order derivative) information for deep neural networks. PYHESSIAN enables fast computations of the top Hessian eigenvalues, the Hessian…

Machine Learning · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael Mahoney

Gaussian Processes (GPs) are flexible, nonparametric Bayesian models widely used for regression and classification because of their ability to capture complex data patterns and quantify predictive uncertainty. However, the O(n^3)…

Machine Learning · Computer Science 2026-01-14 Hua Huang , Tianshi Xu , Yuanzhe Xi , Edmond Chow

At the core of any inference procedure in deep neural networks are dot product operations, which are the component that require the highest computational resources. A common approach to reduce the cost of inference is to reduce its memory…

Machine Learning · Computer Science 2018-12-19 Simon Wiedemann , Klaus-Robert Müller , Wojciech Samek
‹ Prev 1 2 3 10 Next ›