Timezone: »

 
Poster
Model Inversion Networks for Model-Based Optimization
Aviral Kumar · Sergey Levine

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1745
in Poster Session 7 »

This work addresses data-driven optimization problems, where the goal is to find an input that maximizes an unknown score or reward function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein sequences or valid natural images), such model-based optimization problems become exceptionally difficult, since the optimizer must avoid out-of-distribution and invalid inputs. We propose to address such problems with model inversion networks (MINs), which learn an inverse mapping from scores to inputs. MINs can scale to high-dimensional input spaces and leverage offline logged data for both contextual and non-contextual optimization problems. MINs can also handle both purely offline data sources and active data collection. We evaluate MINs on high- dimensional model-based optimization problems over images, protein designs, and neural network controller parameters, and bandit optimization from logged data.

Keywords: Semi-Supervised Learning · Fairness, Accountability, and Transparency · Applications · Algorithms

Author Information

Aviral Kumar (UC Berkeley)
Sergey Levine (UC Berkeley)

More from the Same Authors