Learning an arbitrary mixture of two multinomial logits

07/01/2020
by   Wenpin Tang, et al.
0

In this paper, we consider mixtures of multinomial logistic models (MNL), which are known to ϵ-approximate any random utility model. Despite its long history and broad use, rigorous results are only available for learning a uniform mixture of two MNLs. Continuing this line of research, we study the problem of learning an arbitrary mixture of two MNLs. We show that the identifiability of the mixture models may only fail on an algebraic variety of a negligible measure. This is done by reducing the problem of learning a mixture of two MNLs to the problem of solving a system of univariate quartic equations. We also devise an algorithm to learn any mixture of two MNLs using a polynomial number of samples and a linear number of queries, provided that a mixture of two MNLs over some finite universe is identifiable. Several numerical experiments and conjectures are also presented.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2023

Learning Mixtures of Gaussians with Censored Data

We study the problem of learning mixtures of Gaussians with censored dat...
research
10/06/2020

Learning a mixture of two subspaces over finite fields

We study the problem of learning a mixture of two subspaces over 𝔽_2^n. ...
research
11/03/2018

Learning sparse mixtures of rankings from noisy information

We study the problem of learning an unknown mixture of k rankings over n...
research
11/09/2012

Efficient learning of simplices

We show an efficient algorithm for the following problem: Given uniforml...
research
01/26/2022

Learning Mixtures of Linear Dynamical Systems

We study the problem of learning a mixture of multiple linear dynamical ...
research
07/13/2023

How to perform modeling with independent and preferential data jointly?

Continuous space species distribution models (SDMs) have a long-standing...
research
11/25/2021

Path Guiding Using Spatio-Directional Mixture Models

We propose a learning-based method for light-path construction in path t...

Please sign up or login with your details

Forgot password? Click here to reset