Learning Convex Optimization Models

06/07/2020
by   Akshay Agrawal, et al.
0

A convex optimization model predicts an output from an input by solving a convex optimization problem. The class of convex optimization models is large, and includes as special cases many well-known models like linear and logistic regression. We propose a heuristic for learning the parameters in a convex optimization model given a dataset of input-output pairs, using recently developed methods for differentiating the solution of a convex optimization problem with respect to its parameters. We describe three general classes of convex optimization models, maximum a posteriori (MAP) models, utility maximization models, and agent models, and present a numerical experiment for each.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/19/2019

Learning Convex Optimization Control Policies

Many control policies used in various applications determine the input o...
research
05/22/2023

A Convex Optimization Framework for Regularized Geodesic Distances

We propose a general convex optimization problem for computing regulariz...
research
06/19/2015

Approximate Inference with the Variational Holder Bound

We introduce the Variational Holder (VH) bound as an alternative to Vari...
research
06/27/2018

Two Examples of Convex-Programming-Based High-Dimensional Econometric Estimators

Economists specify high-dimensional models to address heterogeneity in e...
research
06/13/2012

Hierarchical POMDP Controller Optimization by Likelihood Maximization

Planning can often be simpli ed by decomposing the task into smaller tas...
research
05/04/2018

A Convex Approximation of the Relaxed Binaural Beamforming Optimization Problem

The recently proposed relaxed binaural beamforming (RBB) optimization pr...
research
05/04/2023

Off-Road Navigation of Legged Robots Using Linear Transfer Operators

This paper presents the implementation of off-road navigation on legged ...

Please sign up or login with your details

Forgot password? Click here to reset