Learning-Augmented Sketches for Hessians

by   Yi Li, et al.

Sketching is a dimensionality reduction technique where one compresses a matrix by linear combinations that are typically chosen at random. A line of work has shown how to sketch the Hessian to speed up each iteration in a second order method, but such sketches usually depend only on the matrix at hand, and in a number of cases are even oblivious to the input matrix. One could instead hope to learn a distribution on sketching matrices that is optimized for the specific distribution of input matrices. We show how to design learned sketches for the Hessian in the context of second order methods, where we learn potentially different sketches for the different iterations of an optimization procedure. We show empirically that learned sketches, compared with their "non-learned" counterparts, improve the approximation accuracy for important problems, including LASSO, SVM, and matrix estimation with nuclear norm constraints. Several of our schemes can be proven to perform no worse than their unlearned counterparts. Additionally, we show that a smaller sketching dimension of the column space of a tall matrix is possible, assuming an oracle for predicting rows which have a large leverage score.



There are no comments yet.


page 1

page 2

page 3

page 4


Efficient Matrix-Free Approximations of Second-Order Information, with Applications to Pruning and Optimization

Efficiently approximating local curvature information of the loss functi...

Non-PSD Matrix Sketching with Applications to Regression and Optimization

A variety of dimensionality reduction techniques have been applied for c...

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

We introduce AdaHessian, a second order stochastic optimization algorith...

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization

In distributed second order optimization, a standard strategy is to aver...

Fast Approximation of Rotations and Hessians matrices

A new method to represent and approximate rotation matrices is introduce...

On Polyhedral and Second-Order-Cone Decompositions of Semidefinite Optimization Problems

We study a cutting-plane method for semidefinite optimization problems (...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.