4 papers · 1 filter
Leveraging Discrete Function Decomposability for Scientific Design
James C. Bowden, Sergey Levine, Jennifer Listgarten
In the era of AI-driven science and engineering, we often want to design discrete objects in silico according to user-specified properties. For example, we may wish to design a pro…
Is novelty predictable?
Clara Fannjiang, Jennifer Listgarten
Machine learning-based design has gained traction in the sciences, most notably in the design of small molecules, materials, and proteins, with societal implications spanning drug…
Gaussian Process Prior Variational Autoencoders
Francesco Paolo Casale, Adrian V Dalca, Luca Saglietti +2
Variational autoencoders (VAE) are a powerful and widely-used class of models to learn complex data distributions in an unsupervised fashion. One important limitation of VAEs is th…
Design by adaptive sampling
David H. Brookes, Jennifer Listgarten
We present a probabilistic modeling framework and adaptive sampling algorithm wherein unsupervised generative models are combined with black box predictive models to tackle the pro…