Projections onto hyperbolas or bilinear constraint sets in Hilbert spaces

12/03/2021
by   Heinz H. Bauschke, et al.
0

Sets of bilinear constraints are important in various machine learning models. Mathematically, they are hyperbolas in a product space. In this paper, we give a complete formula for projections onto sets of bilinear constraints or hyperbolas in a general Hilbert space.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/29/2021

Interaction of Multiple Tensor Product Operators of the Same Type: an Introduction

Tensor product operators on finite dimensional Hilbert spaces are studie...
research
05/05/2023

A technical note on bilinear layers for interpretability

The ability of neural networks to represent more features than neurons m...
research
05/24/2018

Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products

Vector-valued neural learning has emerged as a promising direction in de...
research
08/15/2022

Reduced Connectivity for Local Bilinear Jacobi Sets

We present a new topological connection method for the local bilinear co...
research
05/09/2017

Improved method for finding optimal formulae for bilinear maps in a finite field

In 2012, Barbulescu, Detrey, Estibals and Zimmermann proposed a new fram...
research
12/06/2019

Bilinear Models for Machine Learning

In this work we define and analyze the bilinear models which replace the...
research
05/26/2023

Bilipschitz group invariants

Consider the quotient of a real Hilbert space by a subgroup of its ortho...

Please sign up or login with your details

Forgot password? Click here to reset