skip to main content

Search for: All records

Award ID contains: 1940224

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Photoswitches are molecules that undergo a reversible, structural isomerization after exposure to different wavelengths of light. The dynamic control offered by molecular photoswitches is favorable for applications in materials chemistry, photopharmacology, and catalysis. Ideal photoswitches absorb visible light and have long-lived metastable isomers. We used high throughput virtual screening to predict the absorption maxima (λmax) of the E-isomer and half-lives (t1/2) of the Z-isomer. However, computing the photophysical and kinetic properties of each entry of a virtual molecular library containing 103–106 entries with density functional theory is prohibitively time-consuming. We applied active search, a machine learning technique to intelligently search a chemical search space of 255991 photoswitches based on 29 known azoarenes and their derivatives. We iteratively trained the active search algorithm based on whether a candidate absorbed visible light (λmax > 450 nm). Active search was found to triple the discovery rate compared to random search. Further, we projected 1962 photoswitches to 2D using the Uniform Manifold Approximation and Projection (umap) algorithm and found that λmax depends on the core, which is tunable with substituents. We then incorporated a second stage of screening with to predict the stabilities of the Z-isomers for the top 1% of candidates. We identifiedmore »four ideal photoswitches that concurrently satisfy λmax > 450 nm and t1/2 > 2 hours; the range of λmax and t1/2 range from 465 to 531 nm and hours to years, respectively.« less
  2. Active search is a learning paradigm where we seek to identify as many members of a rare, valuable class as possible given a labeling budget. Previous work on active search has assumed access to a faithful (and expensive) oracle reporting experimental results. However, some settings offer access to cheaper surrogates such as computational simulation that may aid in the search. We propose a model of multifidelity active search, as well as a novel, computationally efficient policy for this setting that is motivated by state-of-the-art classical policies. Our policy is nonmyopic and budget aware, allowing for a dynamic tradeoff between exploration and exploitation. We evaluate the performance of our solution on real-world datasets and demonstrate significantly better performance than natural benchmarks.
  3. Finite-horizon sequential experimental design (SED) arises naturally in many contexts, including hyperparameter tuning in machine learning among more traditional settings. Computing the optimal policy for such problems requires solving Bellman equations, which are generally intractable. Most existing work resorts to severely myopic approximations by limiting the decision horizon to only a single time-step, which can underweight exploration in favor of exploitation. We present BINOCULARS: Batch-Informed NOnmyopic Choices, Using Long-horizons for Adaptive, Rapid SED, a general framework for deriving efficient, nonmyopic approximations to the optimal experimental policy. Our key idea is simple and surprisingly effective: we first compute a one-step optimal batch of experiments, then select a single point from this batch to evaluate. We realize BINOCULARS for Bayesian optimization and Bayesian quadrature -- two notable example problems with radically different objectives -- and demonstrate that BINOCULARS significantly outperforms significantly outperforms myopic alternatives in real-world scenarios.
  4. Bayesian optimization is a sequential decision making framework for optimizing expensive-to-evaluate black-box functions. Computing a full lookahead policy amounts to solving a highly intractable stochastic dynamic program. Myopic approaches, such as expected improvement, are often adopted in practice, but they ignore the long-term impact of the immediate decision. Existing nonmyopic approaches are mostly heuristic and/or computationally expensive. In this paper, we provide the first efficient implementation of general multi-step lookahead Bayesian optimization, formulated as a sequence of nested optimization problems within a multi-step scenario tree. Instead of solving these problems in a nested way, we equivalently optimize all decision variables in the full tree jointly, in a "one-shot" fashion. Combining this with an efficient method for implementing multi-step Gaussian process "fantasization," we demonstrate that multi-step expected improvement is computationally tractable and exhibits performance superior to existing methods on a wide range of benchmarks.