Relay Variational Inference: A Method for Accelerated Encoderless VI
This addresses a bottleneck in learning generative models without encoders, which is useful for handling missing or uncertain data, though it appears incremental as it builds on encoderless VI methods.
The paper tackles the slow convergence of encoderless variational inference (VI) by introducing Relay VI (RVI), which improves both convergence speed and performance, often outperforming existing encoderless and amortized VI models like VAEs in experiments.
Variational Inference (VI) offers a method for approximating intractable likelihoods. In neural VI, inference of approximate posteriors is commonly done using an encoder. Alternatively, encoderless VI offers a framework for learning generative models from data without encountering suboptimalities caused by amortization via an encoder (e.g. in presence of missing or uncertain data). However, in absence of an encoder, such methods often suffer in convergence due to the slow nature of gradient steps required to learn the approximate posterior parameters. In this paper, we introduce Relay VI (RVI), a framework that dramatically improves both the convergence and performance of encoderless VI. In our experiments over multiple datasets, we study the effectiveness of RVI in terms of convergence speed, loss, representation power and missing data imputation. We find RVI to be a unique tool, often superior in both performance and convergence speed to previously proposed encoderless as well as amortized VI models (e.g. VAE).