Bayesian optimization and attribute adjustment

Stephan Eismann, Daniel Levy, Rui Shu, Stefan Bartzsch, Stefano Ermon
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:1041-1051, 2018.

Abstract

Automatic design via Bayesian optimization holds great promise given the constant increase of available data across domains. However, it faces difficulties from high-dimensional, potentially discrete, search spaces. We propose to probabilistically embed inputs into a lower dimensional, continuous latent space, where we perform gradient-based optimization guided by a Gaussian process. Building on variational au-toncoders, we use both labeled and unlabeled data to guide the encoding and increase its accuracy. In addition, we propose an adversarial extension to render the latent representation invariant with respect to specific design attributes, which allows us to transfer these attributes across structures. We apply the framework both to a functional-protein dataset and to perform optimization of drag coefficients directly over high-dimensional shapes without incorporating domain knowledge or handcrafted features.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-eismann18a, title = {{B}ayesian optimization and attribute adjustment}, author = {Eismann, Stephan and Levy, Daniel and Shu, Rui and Bartzsch, Stefan and Ermon, Stefano}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {1041--1051}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/eismann18a/eismann18a.pdf}, url = {https://proceedings.mlr.press/r16/eismann18a.html}, abstract = {Automatic design via Bayesian optimization holds great promise given the constant increase of available data across domains. However, it faces difficulties from high-dimensional, potentially discrete, search spaces. We propose to probabilistically embed inputs into a lower dimensional, continuous latent space, where we perform gradient-based optimization guided by a Gaussian process. Building on variational au-toncoders, we use both labeled and unlabeled data to guide the encoding and increase its accuracy. In addition, we propose an adversarial extension to render the latent representation invariant with respect to specific design attributes, which allows us to transfer these attributes across structures. We apply the framework both to a functional-protein dataset and to perform optimization of drag coefficients directly over high-dimensional shapes without incorporating domain knowledge or handcrafted features.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Bayesian optimization and attribute adjustment %A Stephan Eismann %A Daniel Levy %A Rui Shu %A Stefan Bartzsch %A Stefano Ermon %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-eismann18a %I PMLR %P 1041--1051 %U https://proceedings.mlr.press/r16/eismann18a.html %V R16 %X Automatic design via Bayesian optimization holds great promise given the constant increase of available data across domains. However, it faces difficulties from high-dimensional, potentially discrete, search spaces. We propose to probabilistically embed inputs into a lower dimensional, continuous latent space, where we perform gradient-based optimization guided by a Gaussian process. Building on variational au-toncoders, we use both labeled and unlabeled data to guide the encoding and increase its accuracy. In addition, we propose an adversarial extension to render the latent representation invariant with respect to specific design attributes, which allows us to transfer these attributes across structures. We apply the framework both to a functional-protein dataset and to perform optimization of drag coefficients directly over high-dimensional shapes without incorporating domain knowledge or handcrafted features. %Z Reissued by PMLR on 04 October 2026.
APA
Eismann, S., Levy, D., Shu, R., Bartzsch, S. & Ermon, S.. (2018). Bayesian optimization and attribute adjustment. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:1041-1051 Available from https://proceedings.mlr.press/r16/eismann18a.html. Reissued by PMLR on 04 October 2026.

Related Material