Objective-Agnostic Enhancement of Molecule Properties via Multi-Stage VAE

no code implementations • 24 Aug 2023 • Chenghui Zhou, Barnabas Poczos

In this paper, we explore applying a multi-stage VAE approach, that can improve manifold recovery on a synthetic dataset, to the field of drug discovery.

Drug Discovery

Improving Molecule Properties Through 2-Stage VAE

no code implementations • 6 Dec 2022 • Chenghui Zhou, Barnabas Poczos

Variational autoencoder (VAE) is a popular method for drug discovery and there had been a great deal of architectures and pipelines proposed to improve its performance.

Drug Discovery

Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias

1 code implementation • ICLR 2022 • Frederic Koehler, Viraj Mehta, Chenghui Zhou, Andrej Risteski

Recent work by Dai and Wipf (2020) proposes a two-stage training algorithm for VAEs, based on a conjecture that in standard VAE training the generator will converge to a solution with 0 variance which is correctly supported on the ground truth manifold.

Unsupervised Program Synthesis for Images By Sampling Without Replacement

no code implementations • 27 Jan 2020 • Chenghui Zhou, Chun-Liang Li, Barnabas Poczos

However, they struggle with the inherent sparsity of meaningful programs in the search space.

Program Synthesis Reinforcement Learning (RL)