Actively Avoiding Nonsense in Generative Models
This addresses the issue of unreliable outputs in generative models for AI practitioners, though it is incremental as it builds on existing learning frameworks.
The paper tackles the problem of generative models producing nonsense due to model error by proposing an active distribution learning approach with an invalidity oracle, showing that improper learning can be done with polynomially many queries while proper learning requires exponentially many.
A generative model may generate utter nonsense when it is fit to maximize the likelihood of observed data. This happens due to "model error," i.e., when the true data generating distribution does not fit within the class of generative models being learned. To address this, we propose a model of active distribution learning using a binary invalidity oracle that identifies some examples as clearly invalid, together with random positive examples sampled from the true distribution. The goal is to maximize the likelihood of the positive examples subject to the constraint of (almost) never generating examples labeled invalid by the oracle. Guarantees are agnostic compared to a class of probability distributions. We show that, while proper learning often requires exponentially many queries to the invalidity oracle, improper distribution learning can be done using polynomially many queries.