- Talks
- Today's Events
- Conferences
Activities
Talks
Investigating the Inference Suboptimality of the Conditional Generative Model and How to Fix It
04/12
2023
Seminar
- Title Investigating the Inference Suboptimality of the Conditional Generative Model and How to Fix It
- Speaker Qi Wang (NUDT)
- Date 10:00 Apr. 12, 2023
- Venue 6420, South Building
Abstract
The recent few years have witnessed the great potential of conditional generative models. Some works like GPT4 and Stable Diffusion exhibit incredible performance in Artificial Intelligence Generated Content (AIGC). This talk will focus on the fundamental issues of conditional generative models and take the neural process model (Garnelo et al., 2018) as an example to investigate the inference suboptimality of variational inference. To close the inference gap, I overview the available optimization objectives and construct the surrogate objective inspired by the variational expectation maximization. The resulting model, referred to as the Self-normalized Importance weighted Neural Process (SI-NP), can learn a more accurate functional prior and has an improvement guarantee concerning the target log-likelihood. Experimental results show the competitive performance of SI-NP over other objectives, guiding the design of inference algorithms for conditional generative models.
Reference: Qi Wang, Marco Federici, & Herke van Hoof, Bridge the Inference Gaps of Neural Processes via Expectation Maximization, ICLR2023.
Invitor: Pan Zhang