Solving an inverse problem with generative models

Abstract

Inverse problems, where we seek the values of inputs to a model that lead to a desired set of outputs, are considered a more challenging problem in science and engineering than forward problems where we compute or measure outputs from known inputs. In this work we demonstrate the use of two generative machine learning methods to solve inverse problems. We compare this approach to two more conventional approaches that use a forward model with nonlinear programming, and the use of a backward model. We illustrate each method on a dataset obtained from a simple remote instrument that has three inputs: the setting of the red, green and blue channels of an RGB LED. We focus on several outputs from a light sensor that measures intensity at 445 nm, 515 nm, 590 nm, and 630 nm. The specific problem we solve is identifying inputs that lead to a specific intensity in three of those channels. We show that generative models can be used to solve this kind of inverse problem, and they have some advantages over the conventional approaches.