Bryce Meredig

Bryce Meredig

Auto-generated profile, based on publicly available information

Bryce Meredig

Citrine Informatics, Redwood City, CA 94063, USA

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 October 2016 in Chemistry of Materials
Verified
Journal Article
Closed access
AOAnton O. Oliynyk
Anton O. Oliynyk
EAErin Antono
Erin Antono
TSTaylor D. Sparks
Taylor D. Sparks
LGLeila Ghadbeigi
Leila Ghadbeigi
MGMichael W. Gaultois
Michael W. Gaultois
AMArthur Mar
Arthur Mar

17 August 2018 in Molecular Systems Design & Engineering
Verified
Journal Article
Open access
PDF file
BMBryce Meredig
Bryce Meredig
EAErin Antono
Erin Antono
CCCarena Church
Carena Church
MHMaxwell Hutchinson
Maxwell Hutchinson
JLJulia Ling
Julia Ling
LWLogan Ward
Logan Ward
Traditional machine learning (ML) metrics overestimate model performance for materials discovery. We introduce (1) leave-one-cluster-out cross-validation (LOCO CV) and (2) a simple nearest-neighbor benchmark to show that model performance in discovery applications strongly depends on the problem, data sampling, and extrapolation. Our results suggest that ML-guided iterative experimentation may outperform standard high-throughput screening for discovering breakthrough materials like high-Tc superconductors with ML.

4 May 2016 in MRS Bulletin
Verified
Journal Article
Closed access
PDF file
JHJoanne Hill
Joanne Hill
GMGregory Mulholland
Gregory Mulholland
KPKristin Persson
Kristin Persson
RSRam Seshadri
Ram Seshadri
CWChris Wolverton
Chris Wolverton
BMBryce Meredig
Bryce Meredig

27 September 2012 in Advanced Energy Materials
Verified
Journal Article
Closed access
PDF file
SKScott Kirklin
Scott Kirklin
BMBryce Meredig
Bryce Meredig
CWChris Wolverton
Chris Wolverton

25 November 2012 in Nature Materials
Verified
Journal Article
Closed access
PDF file
BMBryce Meredig
Bryce Meredig
CWC. Wolverton
C. Wolverton

21 August 2023 in Digital Discovery
Verified
Journal Article
Open access
PDF file
EMEric S. Muckley
Eric S. Muckley
JSJames E. Saal
James E. Saal
BMBryce Meredig
Bryce Meredig
CRChristopher S. Roper
Christopher S. Roper
JMJohn H. Martin
John H. Martin
On average, simple linear models perform equivalently to black box machine learning models on extrapolation tasks.