Parsimonious Potential Energy Surface Expansions Using Dictionary Learning with Multipass Greedy Selection

Moberg, Daniel R.; Jasper, Ahren W.; Davis, Michael J.

doi:10.1021/acs.jpclett.1c02721

Title: Parsimonious Potential Energy Surface Expansions Using Dictionary Learning with Multipass Greedy Selection

Journal Article · 15 September 2021 · Journal of Physical Chemistry Letters

DOI: https://doi.org/10.1021/acs.jpclett.1c02721 · OSTI ID:1854517

^[1];

^[1]

Argonne National Lab. (ANL), Lemont, IL (United States)

Potential energy surfaces fit with basis set expansions have been shown to provide accurate representations of electronic energies and have enabled a variety of high-accuracy dynamics, kinetics, and spectroscopy applications. The number of terms in these expansions scales poorly with system size, a drawback that challenges their use for systems with more than similar to 10 atoms. A solution is presented here using dictionary learning. Subsets of the full set of conventional basis functions are optimized using a newly developed multipass greedy regression method inspired by forward and backward selection methods from the statistics, signal processing, and machine learning literatures. Here, the optimized representations have accuracies comparable to the full set but are 1 or more orders of magnitude smaller, and notably, the number of terms in the optimized multipass greedy expansions scales approximately linearly with the number of atoms.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES). Chemical Sciences, Geosciences & Biosciences Division

Grant/Contract Number:: AC02-06CH11357

OSTI ID:: 1854517

Journal Information:: Journal of Physical Chemistry Letters, Journal Name: Journal of Physical Chemistry Letters Journal Issue: 37 Vol. 12; ISSN 1948-7185

Publisher:: American Chemical SocietyCopyright Statement

Country of Publication:: United States

Language:: English

References (42)

The Elements of Statistical Learning Hastie, Trevor; Tibshirani, Robert; Friedman, Jerome Springer Series in Statistics https://doi.org/10.1007/978-0-387-84858-7	book	January 2009
Sparse and Redundant Representations Elad, Michael Springer New York, NY https://doi.org/10.1007/978-1-4419-7011-4	book	January 2010
The development of a new Morse-oscillator based rotation-vibration Hamiltonian for H3+ Špirko, V.; Jensen, Per; Bunker, P. R. Journal of Molecular Spectroscopy, Vol. 112, Issue 1 https://doi.org/10.1016/0022-2852(85)90203-6	journal	July 1985
Perspectives on CUR decompositions Hamm, Keaton; Huang, Longxiu Applied and Computational Harmonic Analysis, Vol. 48, Issue 3 https://doi.org/10.1016/j.acha.2019.08.006	journal	May 2020
Termolecular chemistry facilitated by radical-radical recombinations and its impact on flame speed predictions Tao, Yujie; Jasper, Ahren W.; Georgievskii, Yuri Proceedings of the Combustion Institute, Vol. 38, Issue 1 https://doi.org/10.1016/j.proci.2020.06.342	journal	January 2021
Neural Network Potential Energy Surfaces for Small Molecules and Reactions Manzhos, Sergei; Carrington, Tucker Chemical Reviews, Vol. 121, Issue 16 https://doi.org/10.1021/acs.chemrev.0c00665	journal	October 2020
Efficient Generation of Permutationally Invariant Potential Energy Surfaces for Large Molecules Conte, Riccardo; Qu, Chen; Houston, Paul L. Journal of Chemical Theory and Computation, Vol. 16, Issue 5 https://doi.org/10.1021/acs.jctc.0c00001	journal	March 2020
Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone Koner, Debasish; Meuwly, Markus Journal of Chemical Theory and Computation, Vol. 16, Issue 9 https://doi.org/10.1021/acs.jctc.0c00535	journal	July 2020
Permutationally Invariant Polynomial Expansions with Unrestricted Complexity Moberg, Daniel R.; Jasper, Ahren W. Journal of Chemical Theory and Computation, Vol. 17, Issue 9 https://doi.org/10.1021/acs.jctc.1c00352	journal	September 2021
Automating the Development of High-Dimensional Reactive Potential Energy Surfaces with the robosurfer Program System Győri, Tibor; Czakó, Gábor Journal of Chemical Theory and Computation, Vol. 16, Issue 1 https://doi.org/10.1021/acs.jctc.9b01006	journal	November 2019
Data-Driven Many-Body Models for Molecular Fluids: CO ₂ /H ₂ O Mixtures as a Case Study Riera, Marc; Yeh, Eric P.; Paesani, Francesco Journal of Chemical Theory and Computation, Vol. 16, Issue 4 https://doi.org/10.1021/acs.jctc.9b01175	journal	March 2020
Global Sensitivity Analysis with Small Sample Sizes: Ordinary Least Squares Approach Davis, Michael J.; Liu, Wei; Sivaramakrishnan, Raghu The Journal of Physical Chemistry A, Vol. 121, Issue 3 https://doi.org/10.1021/acs.jpca.6b09310	journal	January 2017
Sparsity Facilitates Chemical-Reaction Selection for Engine Simulations Magnotti, Gina M.; Wang, Zihan; Liu, Wei The Journal of Physical Chemistry A, Vol. 122, Issue 36 https://doi.org/10.1021/acs.jpca.8b05436	journal	August 2018
Parameterization Strategies for Intermolecular Potentials for Predicting Trajectory-Based Collision Parameters Jasper, Ahren W.; Davis, Michael J. The Journal of Physical Chemistry A, Vol. 123, Issue 16 https://doi.org/10.1021/acs.jpca.9b01918	journal	March 2019
Anharmonic Rovibrational Partition Functions at High Temperatures: Tests of Reduced-Dimensional Models for Systems with up to Three Fluxional Modes Jasper, Ahren W.; Harding, Lawrence B.; Knight, Christopher The Journal of Physical Chemistry A, Vol. 123, Issue 29 https://doi.org/10.1021/acs.jpca.9b03592	journal	June 2019
High-Fidelity Potential Energy Surfaces for Gas-Phase and Gas–Surface Scattering Processes from Machine Learning Jiang, Bin; Li, Jun; Guo, Hua The Journal of Physical Chemistry Letters, Vol. 11, Issue 13 https://doi.org/10.1021/acs.jpclett.0c00989	journal	June 2020
Breaking the Coupled Cluster Barrier for Machine-Learned Potentials of Large Molecules: The Case of 15-Atom Acetylacetone Qu, Chen; Houston, Paul L.; Conte, Riccardo The Journal of Physical Chemistry Letters, Vol. 12, Issue 20 https://doi.org/10.1021/acs.jpclett.1c01142	journal	May 2021
Development of a “First Principles” Water Potential with Flexible Monomers: Dimer Potential Energy Surface, VRT Spectrum, and Second Virial Coefficient Babin, Volodymyr; Leforestier, Claude; Paesani, Francesco Journal of Chemical Theory and Computation, Vol. 9, Issue 12 https://doi.org/10.1021/ct400863t	journal	November 2013
Unimolecular dissociation dynamics of vibrationally activated CH3CHOO Criegee intermediates to OH radical products Kidwell, Nathanael M.; Li, Hongwei; Wang, Xiaohong Nature Chemistry, Vol. 8, Issue 5 https://doi.org/10.1038/nchem.2488	journal	April 2016
Full-dimensional potential energy surface for acetylacetone and tunneling splittings Qu, Chen; Conte, Riccardo; Houston, Paul L. Physical Chemistry Chemical Physics, Vol. 23, Issue 13 https://doi.org/10.1039/D0CP04221H	journal	January 2021
Global ab initio ground-state potential energy surface of N ₄ Paukku, Yuliya; Yang, Ke R.; Varga, Zoltan The Journal of Chemical Physics, Vol. 139, Issue 4 https://doi.org/10.1063/1.4811653	journal	July 2013
Communication: A benchmark-quality, full-dimensional ab initio potential energy surface for Ar-HOCO Conte, Riccardo; Houston, Paul L.; Bowman, Joel M. The Journal of Chemical Physics, Vol. 140, Issue 15 https://doi.org/10.1063/1.4871371	journal	April 2014
On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice Reddy, Sandeep K.; Straight, Shelby C.; Bajaj, Pushp The Journal of Chemical Physics, Vol. 145, Issue 19 https://doi.org/10.1063/1.4967719	journal	November 2016
A fragmented, permutationally invariant polynomial approach for potential energy surfaces of large molecules: Application to N -methyl acetamide Qu, Chen; Bowman, Joel M. The Journal of Chemical Physics, Vol. 150, Issue 14 https://doi.org/10.1063/1.5092794	journal	April 2019
Full and fragmented permutationally invariant polynomial potential energy surfaces for trans and cis N -methyl acetamide and isomerization saddle points Nandi, Apurba; Qu, Chen; Bowman, Joel M. The Journal of Chemical Physics, Vol. 151, Issue 8 https://doi.org/10.1063/1.5119348	journal	August 2019
Permutationally invariant polynomial potential energy surfaces for tropolone and H and D atom tunneling dynamics Houston, Paul; Conte, Riccardo; Qu, Chen The Journal of Chemical Physics, Vol. 153, Issue 2 https://doi.org/10.1063/5.0011973	journal	July 2020
CUR matrix decompositions for improved data analysis Mahoney, Michael W.; Drineas, Petros Proceedings of the National Academy of Sciences, Vol. 106, Issue 3 https://doi.org/10.1073/pnas.0803205106	journal	January 2009
Permutationally invariant potential energy surfaces in high dimensionality Braams, Bastiaan J.; Bowman, Joel M. International Reviews in Physical Chemistry, Vol. 28, Issue 4 https://doi.org/10.1080/01442350903234923	journal	October 2009
Single- and multireference electronic structure calculations for constructing potential energy surfaces Dawes, Richard; Ndengué, Steve A. International Reviews in Physical Chemistry, Vol. 35, Issue 3 https://doi.org/10.1080/0144235X.2016.1195102	journal	June 2016
Potential energy surfaces from high fidelity fitting of ab initio points: the permutation invariant polynomial - neural network approach Jiang, Bin; Li, Jun; Guo, Hua International Reviews in Physical Chemistry, Vol. 35, Issue 3 https://doi.org/10.1080/0144235X.2016.1200347	journal	July 2016
MIP-BOOST: Efficient and Effective L ₀ Feature Selection for Linear Regression Kenney, Ana; Chiaromonte, Francesca; Felici, Giovanni Journal of Computational and Graphical Statistics, Vol. 30, Issue 3 https://doi.org/10.1080/10618600.2020.1845184	journal	January 2021
Dictionaries for Sparse Representation Modeling Rubinstein, Ron; Bruckstein, Alfred M.; Elad, Michael Proceedings of the IEEE, Vol. 98, Issue 6 https://doi.org/10.1109/JPROC.2010.2040551	journal	June 2010
Dictionary Learning Tosic, Ivana; Frossard, Pascal IEEE Signal Processing Magazine, Vol. 28, Issue 2 https://doi.org/10.1109/MSP.2010.939537	journal	March 2011
Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit Tropp, Joel A.; Gilbert, Anna C. IEEE Transactions on Information Theory, Vol. 53, Issue 12 https://doi.org/10.1109/TIT.2007.909108	journal	December 2007
Adaptive Forward-Backward Greedy Algorithm for Learning Sparse Representations Zhang, Tong IEEE Transactions on Information Theory, Vol. 57, Issue 7 https://doi.org/10.1109/TIT.2011.2146690	journal	July 2011
Regression shrinkage and selection via the lasso: a retrospective: Regression Shrinkage and Selection via the Lasso Tibshirani, Robert Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 73, Issue 3 https://doi.org/10.1111/j.1467-9868.2011.00771.x	journal	April 2011
Regression Shrinkage and Selection Via the Lasso Tibshirani, Robert Journal of the Royal Statistical Society: Series B (Methodological), Vol. 58, Issue 1 https://doi.org/10.1111/j.2517-6161.1996.tb02080.x	journal	January 1996
An Improved Approximation Algorithm for the Column Subset Selection Problem Boutsidis, Christos; Mahoney, Michael W.; Drineas, Petros Proceedings of the Twentieth Annual ACM-SIAM Symposium on Discrete Algorithms https://doi.org/10.1137/1.9781611973068.105	conference	December 2013
Updating the Inverse of a Matrix Hager, William W. SIAM Review, Vol. 31, Issue 2, p. 221-239 https://doi.org/10.1137/1031049	journal	June 1989
Near-Optimal Column-Based Matrix Reconstruction Boutsidis, Christos; Drineas, Petros; Magdon-Ismail, Malik SIAM Journal on Computing, Vol. 43, Issue 2 https://doi.org/10.1137/12086755X	journal	January 2014
On the Optimality of the Backward Greedy Algorithm for the Subset Selection Problem Couvreur, Christophe; Bresler, Yoram SIAM Journal on Matrix Analysis and Applications, Vol. 21, Issue 3 https://doi.org/10.1137/S0895479898332928	journal	January 2000
Statistical Learning with Sparsity Hastie, Trevor; Tibshirani, Robert; Wainwright, Martin Chapman and Hall/CRC https://doi.org/10.1201/b18401	book	May 2015

Similar Records

Bayesian K-SVD Using Fast Variational Inference

Journal Article · 2017 · IEEE Transactions on Image Processing · OSTI ID:1487464

Serra, Juan G.; Testa, Matteo; Molina, Rafael; +1 more

First- and Second-Order Methods for Online Convolutional Dictionary Learning

Journal Article · 2018 · SIAM Journal on Imaging Sciences · OSTI ID:1475355

Liu, Jialin; Garcia-Cardona, Cristina; Wohlberg, Brendt; +1 more

Submodular optimization problems and greedy strategies: A survey

Journal Article · 2020 · Discrete Event Dynamic Systems · OSTI ID:1603264

Liu, Yajing; Chong, Edwin K. P.; Pezeshki, Ali; +1 more

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
basis sets
chemical calculations
computational chemistry
feature selection
kinetic parameters
machine learning
permutationally invariant polynomials
potential energy surfaces

Title: Parsimonious Potential Energy Surface Expansions Using Dictionary Learning with Multipass Greedy Selection

Citation Formats

References (42)

Similar Records

Related Subjects