Sterling G. Baird

icon indicating a website link https://acceleration.utoronto.ca/researcher/sterling-baird icon indicating an email [email protected]

icon company @AccelerationConsortium (UoT) @sparks-baird (UoU) icon location Toronto, ON icon location I direct training programs at the @AccelerationConsortium for materials discovery enabled by Bayesian optimization and self-driving labs. Former @sp8rks group

Results 553 comments of Sterling G. Baird

On the validity score (improving understanding and/or modifications)

@keeeto I like the idea of considering both structural and chemical validity, which is in line with some other recent changes https://github.com/sparks-baird/matbench-genmetrics/issues/39#issuecomment-1205587728. I've been hoping to use SkipAtom at some...

Models.FULLYBAYESIAN vs. Models.SAASBO and SAASBO kwargs

kwargs not being added when switching

Models.FULLYBAYESIAN vs. Models.SAASBO and SAASBO kwargs

Related #87

Implement multi-fidelity optimization

Need to set fidelity row to hidden for now

Implement multi-fidelity optimization

> I've been trying to implement this in the Service API: [Ax Issue 2514](https://github.com/facebook/Ax/issues/2514). Might be useful here (if I can verify its correctness!) Thanks! I have https://github.com/sgbaird/honegumi/blob/main/scripts%2Frefreshers%2Fcontinuous_multi_fidelity.py though I'm...

Implement multi-fidelity optimization

Fidelity not complete, but at least removed from visibility for now.

[Feature Request] Add input constructors for all acquisition functions

- qNegIntegratedPosteriorVariance https://github.com/facebook/Ax/issues/1557 https://github.com/facebook/Ax/issues/1312

Check feasibility of sharing link to a specific honegumi configuration using URL parameters

Possibly the solution: https://stackoverflow.com/a/22607328/13697228. i.e., use Javascript to update the table, and would work best as a bi-directional piece. This would require some careful implementation, including keeping honegumi reusable #89

Add data of last modification to tutorials and concept docs

I've enabled this on similar projects, so it should be straightforward. Thanks! Get Outlook for Android ________________________________ From: Andrew ***@***.***> Sent: Saturday, August 24, 2024 7:44:35 PM To: sgbaird/honegumi ***@***.***>...

[FEATURE REQUEST]: Pool-based learning within Ax (i.e. allow Ax to sample from a pre-selected finite set of feasible arms only)

@CompRhys, maybe relevant (and would help if you could clarify what matches / doesn't match relative to these topics) - https://github.com/facebook/Ax/issues/706 - https://github.com/facebook/Ax/issues/771 Trying to understand if pool-based learning is...