Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases

10/01/2020
by   Chris Wendler, et al.
16

Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain. In this work, we present a new family of algorithms for learning Fourier-sparse set functions. They require at most nk - k log_2 k + k queries (set function evaluations), under mild conditions on the Fourier coefficients, where n is the size of the ground set and k the number of non-zero Fourier coefficients. In contrast to other work that focused on the orthogonal Walsh-Hadamard transform, our novel algorithms operate with recently introduced non-orthogonal Fourier transforms that offer different notions of Fourier-sparsity. These naturally arise when modeling, e.g., sets of items forming substitutes and complements. We demonstrate effectiveness on several real-world applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/07/2013

Clifford Fourier-Mellin transform with two real square roots of -1 in Cl(p,q), p+q=2

We describe a non-commutative generalization of the complex Fourier-Mell...
research
10/13/2019

Fast Fourier Sparsity Testing

A function f : F_2^n →R is s-sparse if it has at most s non-zero Fourier...
research
07/21/2021

How many Fourier coefficients are needed?

We are looking at families of functions or measures on the torus (in dim...
research
11/20/2019

A family of orthogonal rational functions and other orthogonal systems with a skew-Hermitian differentiation matrix

In this paper we explore orthogonal systems in L_2(R) which give rise to...
research
04/15/2020

Characterization of Sobolev spaces by their Fourier coefficients in axisymmetric domains

Using Fourier series representations of functions on axisymmetric domain...
research
07/24/2020

A short letter on the dot product between rotated Fourier transforms

Spatial Semantic Pointers (SSPs) have recently emerged as a powerful too...
research
09/22/2020

Fourier Analysis-based Iterative Combinatorial Auctions

Recent advances in Fourier analysis have brought new tools to efficientl...

Please sign up or login with your details

Forgot password? Click here to reset