Cash App Labs Modifies the Very Deep VAE to Achieve a 2.6x Speedup and 20x Memory Reduction

Researchers from Cash App Labs introduce simple modifications to the Very Deep Variational Autoencoder (VAE) that speedup convergence by 2.6x, save up to 20x in memory, and improve stability during training. Their modified VDVAE achieves state-of-the-art performance on seven commonly used image datasets.

ai app artificial intelligence deep-neural-networks machine learning machine learning & data science maximum likelihood estimation memory ml research technology variational autoencoders