2024
|
Tan, Jin Da; Low, Andre K Y; Ying, Shannon Thoi Rui; Tan, Sze Yu; Zhao, Wenguang; Lim, Yee-Fun; Li, Qianxiao; Khan, Saif A; Ramalingam, Balamurugan; Hippalgaonkar, Kedar Multi-objective synthesis optimization and kinetics of a sustainable terpolymer DIGITAL DISCOVERY, 2024, DOI: 10.1039/d4dd00233d. Abstract | BibTeX | Endnote @article{ISI:001349870400001,
title = {Multi-objective synthesis optimization and kinetics of a sustainable terpolymer},
author = {Jin Da Tan and Andre K Y Low and Shannon Thoi Rui Ying and Sze Yu Tan and Wenguang Zhao and Yee-Fun Lim and Qianxiao Li and Saif A Khan and Balamurugan Ramalingam and Kedar Hippalgaonkar},
doi = {10.1039/d4dd00233d},
times_cited = {0},
year = {2024},
date = {2024-11-04},
journal = {DIGITAL DISCOVERY},
publisher = {ROYAL SOC CHEMISTRY},
address = {THOMAS GRAHAM HOUSE, SCIENCE PARK, MILTON RD, CAMBRIDGE CB4 0WF, CAMBS, ENGLAND},
abstract = {The properties of polymers are primarily influenced by their monomer constituents, functional groups, and their mode of linkages. Copolymers, synthesized from multiple monomers, offer unique material properties compared to their homopolymers. Optimizing the synthesis of terpolymers is a complex and labor-intensive task due to variations in monomer reactivity and their compositional shifts throughout the polymerization process. The present work focuses on synthesizing a new terpolymer from styrene, myrcene, and dibutyl itaconate (DBI) monomers with the goal of achieving a high glass transition temperature (Tg) in the resulting terpolymer. While the copolymerization of pairwise combinations of styrene, myrcene, and DBI have been previously investigated, the terpolymerization of all three at once remains unexplored. Terpolymers with monomers like styrene would provide high glass transition temperatures as the resultant polymers exhibit a rigid glassy state at ambient temperatures. Conversely, minimizing styrene incorporation also reduces reliance on petrochemical-derived monomer sources for terpolymer synthesis, thus enhancing the sustainability of terpolymer usage. To balance the objectives of maximizing Tg while minimizing styrene incorporation, we employ multi-objective Bayesian optimization to efficiently sample in a design space comprising 5 experimental parameters. We perform two iterations of optimization for a total of 89 terpolymers, reporting terpolymers with a Tg above ambient temperature while retaining less than 50% styrene incorporation. This underscores the potential for exploring and utilizing renewable monomers such as myrcene and DBI, to foster sustainability in polymer synthesis. Additionally, the dataset enables the calculation of ternary reactivity ratios using a system of ordinary differential equations based on the terminal model, providing valuable insights into the reactivity of monomers in complex ternary systems compared to binary copolymer systems. This approach reveals the nuanced kinetics of terpolymerization, further informing the synthesis of polymers with desired properties.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The properties of polymers are primarily influenced by their monomer constituents, functional groups, and their mode of linkages. Copolymers, synthesized from multiple monomers, offer unique material properties compared to their homopolymers. Optimizing the synthesis of terpolymers is a complex and labor-intensive task due to variations in monomer reactivity and their compositional shifts throughout the polymerization process. The present work focuses on synthesizing a new terpolymer from styrene, myrcene, and dibutyl itaconate (DBI) monomers with the goal of achieving a high glass transition temperature (Tg) in the resulting terpolymer. While the copolymerization of pairwise combinations of styrene, myrcene, and DBI have been previously investigated, the terpolymerization of all three at once remains unexplored. Terpolymers with monomers like styrene would provide high glass transition temperatures as the resultant polymers exhibit a rigid glassy state at ambient temperatures. Conversely, minimizing styrene incorporation also reduces reliance on petrochemical-derived monomer sources for terpolymer synthesis, thus enhancing the sustainability of terpolymer usage. To balance the objectives of maximizing Tg while minimizing styrene incorporation, we employ multi-objective Bayesian optimization to efficiently sample in a design space comprising 5 experimental parameters. We perform two iterations of optimization for a total of 89 terpolymers, reporting terpolymers with a Tg above ambient temperature while retaining less than 50% styrene incorporation. This underscores the potential for exploring and utilizing renewable monomers such as myrcene and DBI, to foster sustainability in polymer synthesis. Additionally, the dataset enables the calculation of ternary reactivity ratios using a system of ordinary differential equations based on the terminal model, providing valuable insights into the reactivity of monomers in complex ternary systems compared to binary copolymer systems. This approach reveals the nuanced kinetics of terpolymerization, further informing the synthesis of polymers with desired properties. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AUDa Tan, J
Low, AKY
Ying, STR
Tan, SY
Zhao, WG
Lim, YF
Li, QX
Khan, SA
Ramalingam, B
Hippalgaonkar, K
- AFJin Da Tan
Andre K Y Low
Shannon Thoi Rui Ying
Sze Yu Tan
Wenguang Zhao
Yee-Fun Lim
Qianxiao Li
Saif A Khan
Balamurugan Ramalingam
Kedar Hippalgaonkar
- TIMulti-objective synthesis optimization and kinetics of a sustainable terpolymer
- SODIGITAL DISCOVERY
- LAEnglish
- DTArticle
- IDCOPOLYMERS; POLYMERS; POLYMERIZATION; MYRCENE; STYRENE; BLOCK
- ABThe properties of polymers are primarily influenced by their monomer constituents, functional groups, and their mode of linkages. Copolymers, synthesized from multiple monomers, offer unique material properties compared to their homopolymers. Optimizing the synthesis of terpolymers is a complex and labor-intensive task due to variations in monomer reactivity and their compositional shifts throughout the polymerization process. The present work focuses on synthesizing a new terpolymer from styrene, myrcene, and dibutyl itaconate (DBI) monomers with the goal of achieving a high glass transition temperature (Tg) in the resulting terpolymer. While the copolymerization of pairwise combinations of styrene, myrcene, and DBI have been previously investigated, the terpolymerization of all three at once remains unexplored. Terpolymers with monomers like styrene would provide high glass transition temperatures as the resultant polymers exhibit a rigid glassy state at ambient temperatures. Conversely, minimizing styrene incorporation also reduces reliance on petrochemical-derived monomer sources for terpolymer synthesis, thus enhancing the sustainability of terpolymer usage. To balance the objectives of maximizing Tg while minimizing styrene incorporation, we employ multi-objective Bayesian optimization to efficiently sample in a design space comprising 5 experimental parameters. We perform two iterations of optimization for a total of 89 terpolymers, reporting terpolymers with a Tg above ambient temperature while retaining less than 50% styrene incorporation. This underscores the potential for exploring and utilizing renewable monomers such as myrcene and DBI, to foster sustainability in polymer synthesis. Additionally, the dataset enables the calculation of ternary reactivity ratios using a system of ordinary differential equations based on the terminal model, providing valuable insights into the reactivity of monomers in complex ternary systems compared to binary copolymer systems. This approach reveals the nuanced kinetics of terpolymerization, further informing the synthesis of polymers with desired properties.
- C1[Da Tan, Jin; Low, Andre K. Y.; Tan, Sze Yu; Lim, Yee-Fun; Ramalingam, Balamurugan; Hippalgaonkar, Kedar] ASTAR, Inst Mat Res & Engn IMRE, 2 Fusionopolis Way,Innovis 08-03, Singapore 138634, Singapore.
[Da Tan, Jin; Khan, Saif A.] Natl Univ Singapore, Grad Sch, Integrat Sci & Engn Programme, 21 Lower Kent Ridge Rd, Singapore 119077, Singapore.
[Low, Andre K. Y.; Hippalgaonkar, Kedar] Nanyang Technol Univ, Sch Mat Sci & Engn, Singapore 639798, Singapore.
[Ying, Shannon Thoi Rui; Zhao, Wenguang; Lim, Yee-Fun; Ramalingam, Balamurugan] ASTAR, Inst Sustainabil Chem Energy & Environm ISCE2, 1 Pesek Rd, Singapore 627833, Singapore.
[Li, Qianxiao; Hippalgaonkar, Kedar] Natl Univ Singapore, Inst Funct Intelligent Mat, 4 Sci Dr 2, Singapore 117544, Singapore.
[Li, Qianxiao] Natl Univ Singapore, Dept Math, Singapore 119076, Singapore.
[Khan, Saif A.] Natl Univ Singapore, Dept Chem & Biomol Engn, 4 Engn Dr 4, Singapore 117585, Singapore - C3Agency for Science Technology & Research (A*STAR); A*STAR - Institute of Materials Research & Engineering (IMRE); National University of Singapore; Nanyang Technological University; Agency for Science Technology & Research (A*STAR); Institute for Functional Intelligent Materials (I-FIM); National University of Singapore; National University of Singapore; National University of Singapore
- RPRamalingam, B (corresponding author), ASTAR, Inst Mat Res & Engn IMRE, 2 Fusionopolis Way,Innovis 08-03, Singapore 138634, Singapore; Hippalgaonkar, K (corresponding author), Nanyang Technol Univ, Sch Mat Sci & Engn, Singapore 639798, Singapore; Ramalingam, B (corresponding author), ASTAR, Inst Sustainabil Chem Energy & Environm ISCE2, 1 Pesek Rd, Singapore 627833, Singapore; Hippalgaonkar, K (corresponding author), Natl Univ Singapore, Inst Funct Intelligent Mat, 4 Sci Dr 2, Singapore 117544, Singapore
- FUNational Research Foundation Singapore [M24N4b0034]; AME Programmatic Fund [NRF-CRP25-2020-0002]; National Research Foundation's Competitive Research Programme (NRF-CRP) in Singapore [C231218004]; Horizontal Technology Coordinating Office of A*STAR
- FXK. H. and B. R. acknowledge funding from the Materials Generative Design and Testing Framework (MAT-GDT) Program at A*STAR, provided through the AME Programmatic Fund (Grant No. M24N4b0034). K. H. acknowledges the National Research Foundation's Competitive Research Programme (NRF-CRP) in Singapore (Grant No. NRF-CRP25-2020-0002). BR thanks the Horizontal Technology Coordinating Office of A*STAR for seed funding under project No. C231218004.
- NR43
- TC0
- Z90
- U10
- U20
- PUROYAL SOC CHEMISTRY
- PICAMBRIDGE
- PATHOMAS GRAHAM HOUSE, SCIENCE PARK, MILTON RD, CAMBRIDGE CB4 0WF, CAMBS, ENGLAND
- J9DIGIT DISCOV
- JIDigit. Discov.
- PDNOV 4
- PY2024
- DI10.1039/d4dd00233d
- PG9
- WCChemistry, Multidisciplinary; Computer Science, Interdisciplinary Applications
- SCChemistry; Computer Science
- GAL3P3S
- UTWOS:001349870400001
- ER
- EF
|
Zhu, Aiqing; Li, Qianxiao DynGMA: A robust approach for learning stochastic differential equations from data JOURNAL OF COMPUTATIONAL PHYSICS, 513 , 2024, DOI: 10.1016/j.jcp.2024.113200. Abstract | BibTeX | Endnote @article{ISI:001362295900001,
title = {DynGMA: A robust approach for learning stochastic differential equations from data},
author = {Aiqing Zhu and Qianxiao Li},
doi = {10.1016/j.jcp.2024.113200},
times_cited = {0},
issn = {0021-9991},
year = {2024},
date = {2024-09-15},
journal = {JOURNAL OF COMPUTATIONAL PHYSICS},
volume = {513},
publisher = {ACADEMIC PRESS INC ELSEVIER SCIENCE},
address = {525 B ST, STE 1900, SAN DIEGO, CA 92101-4495 USA},
abstract = {Learning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and construct likelihood-based loss by approximating the transition density to train these networks. However, these methods often rely on one-step stochastic numerical schemes, necessitating data with sufficiently high time resolution. In this paper, we introduce novel approximations to the transition density of the parameterized SDE: a Gaussian density approximation inspired by the random perturbation theory of dynamical systems, and its extension, the dynamical Gaussian mixture approximation (DynGMA). Benefiting from the robust density approximation, our method exhibits superior accuracy compared to baseline methods in learning the fully unknown drift and diffusion functions and computing the invariant distribution from trajectory data. And it is capable of handling trajectory data with low time resolution and variable, even uncontrollable, time step sizes, such as data generated from Gillespie's stochastic simulations. We then conduct several experiments across various scenarios to verify the advantages and robustness of the proposed method.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Learning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and construct likelihood-based loss by approximating the transition density to train these networks. However, these methods often rely on one-step stochastic numerical schemes, necessitating data with sufficiently high time resolution. In this paper, we introduce novel approximations to the transition density of the parameterized SDE: a Gaussian density approximation inspired by the random perturbation theory of dynamical systems, and its extension, the dynamical Gaussian mixture approximation (DynGMA). Benefiting from the robust density approximation, our method exhibits superior accuracy compared to baseline methods in learning the fully unknown drift and diffusion functions and computing the invariant distribution from trajectory data. And it is capable of handling trajectory data with low time resolution and variable, even uncontrollable, time step sizes, such as data generated from Gillespie's stochastic simulations. We then conduct several experiments across various scenarios to verify the advantages and robustness of the proposed method. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AUZhu, AQ
Li, QX
- AFAiqing Zhu
Qianxiao Li
- TIDynGMA: A robust approach for learning stochastic differential equations from data
- SOJOURNAL OF COMPUTATIONAL PHYSICS
- LAEnglish
- DTArticle
- DENeural Networks; Learning Dynamics; Maximum Likelihood Estimation; Stochastic Differential Equations; Invariant Distribution
- IDMAXIMUM-LIKELIHOOD-ESTIMATION; DIFFUSIONS
- ABLearning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and construct likelihood-based loss by approximating the transition density to train these networks. However, these methods often rely on one-step stochastic numerical schemes, necessitating data with sufficiently high time resolution. In this paper, we introduce novel approximations to the transition density of the parameterized SDE: a Gaussian density approximation inspired by the random perturbation theory of dynamical systems, and its extension, the dynamical Gaussian mixture approximation (DynGMA). Benefiting from the robust density approximation, our method exhibits superior accuracy compared to baseline methods in learning the fully unknown drift and diffusion functions and computing the invariant distribution from trajectory data. And it is capable of handling trajectory data with low time resolution and variable, even uncontrollable, time step sizes, such as data generated from Gillespie's stochastic simulations. We then conduct several experiments across various scenarios to verify the advantages and robustness of the proposed method.
- C1[Zhu, Aiqing; Li, Qianxiao] Natl Univ Singapore, Dept Math, 10 Lower Kent Ridge Rd, Singapore 119076, Singapore.
[Li, Qianxiao] Natl Univ Singapore, Inst Funct Intelligent Mat, 4 Sci Dr 2, Singapore 117544, Singapore - C3National University of Singapore; National University of Singapore; Institute for Functional Intelligent Materials (I-FIM)
- RPLi, QX (corresponding author), Natl Univ Singapore, Dept Math, 10 Lower Kent Ridge Rd, Singapore 119076, Singapore
- FUNational Research Foundation, Singapore [AISG3-RP-2022-028]; NRF fellowship [NRF-NRFF13-2021-0005]
- FXThis project is supported by the National Research Foundation, Singapore, under its AI Singapore Programme (AISG Award No: AISG3-RP-2022-028) and the NRF fellowship (project No. NRF-NRFF13-2021-0005).
- NR48
- TC0
- Z90
- U10
- U20
- PUACADEMIC PRESS INC ELSEVIER SCIENCE
- PISAN DIEGO
- PA525 B ST, STE 1900, SAN DIEGO, CA 92101-4495 USA
- SN0021-9991
- J9J COMPUT PHYS
- JIJ. Comput. Phys.
- PDSEP 15
- PY2024
- VL513
- DI10.1016/j.jcp.2024.113200
- PG21
- WCComputer Science, Interdisciplinary Applications; Physics, Mathematical
- SCComputer Science; Physics
- GAN1V6J
- UTWOS:001362295900001
- ER
- EF
|
Low, Andre K Y; Mekki-Berrada, Flore; Gupta, Abhishek; Ostudin, Aleksandr; Xie, Jiaxun; Vissol-Gaudin, Eleonore; Lim, Yee-Fun; Li, Qianxiao; Ong, Yew Soon; Khan, Saif A; Hippalgaonkar, Kedar Evolution-guided Bayesian optimization for constrained multi-objective optimization in self-driving labs NPJ COMPUTATIONAL MATERIALS, 10 (1), 2024, DOI: 10.1038/s41524-024-01274-x. Abstract | BibTeX | Endnote @article{ISI:001221677000002,
title = {Evolution-guided Bayesian optimization for constrained multi-objective optimization in self-driving labs},
author = {Andre K Y Low and Flore Mekki-Berrada and Abhishek Gupta and Aleksandr Ostudin and Jiaxun Xie and Eleonore Vissol-Gaudin and Yee-Fun Lim and Qianxiao Li and Yew Soon Ong and Saif A Khan and Kedar Hippalgaonkar},
doi = {10.1038/s41524-024-01274-x},
times_cited = {2},
year = {2024},
date = {2024-05-13},
journal = {NPJ COMPUTATIONAL MATERIALS},
volume = {10},
number = {1},
publisher = {NATURE PORTFOLIO},
address = {HEIDELBERGER PLATZ 3, BERLIN, 14197, GERMANY},
abstract = {The development of automated high-throughput experimental platforms has enabled fast sampling of high-dimensional decision spaces. To reach target properties efficiently, these platforms are increasingly paired with intelligent experimental design. However, current optimizers show limitations in maintaining sufficient exploration/exploitation balance for problems dealing with multiple conflicting objectives and complex constraints. Here, we devise an Evolution-Guided Bayesian Optimization (EGBO) algorithm that integrates selection pressure in parallel with a q-Noisy Expected Hypervolume Improvement (qNEHVI) optimizer; this not only solves for the Pareto Front (PF) efficiently but also achieves better coverage of the PF while limiting sampling in the infeasible space. The algorithm is developed together with a custom self-driving lab for seed-mediated silver nanoparticle synthesis, targeting 3 objectives (1) optical properties, (2) fast reaction, and (3) minimal seed usage alongside complex constraints. We demonstrate that, with appropriate constraint handling, EGBO performance improves upon state-of-the-art qNEHVI. Furthermore, across various synthetic multi-objective problems, EGBO shows significative hypervolume improvement, revealing the synergy between selection pressure and the qNEHVI optimizer. We also demonstrate EGBO's good coverage of the PF as well as comparatively better ability to propose feasible solutions. We thus propose EGBO as a general framework for efficiently solving constrained multi-objective problems in high-throughput experimentation platforms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The development of automated high-throughput experimental platforms has enabled fast sampling of high-dimensional decision spaces. To reach target properties efficiently, these platforms are increasingly paired with intelligent experimental design. However, current optimizers show limitations in maintaining sufficient exploration/exploitation balance for problems dealing with multiple conflicting objectives and complex constraints. Here, we devise an Evolution-Guided Bayesian Optimization (EGBO) algorithm that integrates selection pressure in parallel with a q-Noisy Expected Hypervolume Improvement (qNEHVI) optimizer; this not only solves for the Pareto Front (PF) efficiently but also achieves better coverage of the PF while limiting sampling in the infeasible space. The algorithm is developed together with a custom self-driving lab for seed-mediated silver nanoparticle synthesis, targeting 3 objectives (1) optical properties, (2) fast reaction, and (3) minimal seed usage alongside complex constraints. We demonstrate that, with appropriate constraint handling, EGBO performance improves upon state-of-the-art qNEHVI. Furthermore, across various synthetic multi-objective problems, EGBO shows significative hypervolume improvement, revealing the synergy between selection pressure and the qNEHVI optimizer. We also demonstrate EGBO's good coverage of the PF as well as comparatively better ability to propose feasible solutions. We thus propose EGBO as a general framework for efficiently solving constrained multi-objective problems in high-throughput experimentation platforms. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AULow, AKY
Mekki-Berrada, F
Gupta, A
Ostudin, A
Xie, JX
Vissol-Gaudin, E
Lim, YF
Li, QX
Ong, YS
Khan, SA
Hippalgaonkar, K
- AFAndre K Y Low
Flore Mekki-Berrada
Abhishek Gupta
Aleksandr Ostudin
Jiaxun Xie
Eleonore Vissol-Gaudin
Yee-Fun Lim
Qianxiao Li
Yew Soon Ong
Saif A Khan
Kedar Hippalgaonkar
- TIEvolution-guided Bayesian optimization for constrained multi-objective optimization in self-driving labs
- SONPJ COMPUTATIONAL MATERIALS
- LAEnglish
- DTArticle
- IDGAUSSIAN-PROCESSES
- ABThe development of automated high-throughput experimental platforms has enabled fast sampling of high-dimensional decision spaces. To reach target properties efficiently, these platforms are increasingly paired with intelligent experimental design. However, current optimizers show limitations in maintaining sufficient exploration/exploitation balance for problems dealing with multiple conflicting objectives and complex constraints. Here, we devise an Evolution-Guided Bayesian Optimization (EGBO) algorithm that integrates selection pressure in parallel with a q-Noisy Expected Hypervolume Improvement (qNEHVI) optimizer; this not only solves for the Pareto Front (PF) efficiently but also achieves better coverage of the PF while limiting sampling in the infeasible space. The algorithm is developed together with a custom self-driving lab for seed-mediated silver nanoparticle synthesis, targeting 3 objectives (1) optical properties, (2) fast reaction, and (3) minimal seed usage alongside complex constraints. We demonstrate that, with appropriate constraint handling, EGBO performance improves upon state-of-the-art qNEHVI. Furthermore, across various synthetic multi-objective problems, EGBO shows significative hypervolume improvement, revealing the synergy between selection pressure and the qNEHVI optimizer. We also demonstrate EGBO's good coverage of the PF as well as comparatively better ability to propose feasible solutions. We thus propose EGBO as a general framework for efficiently solving constrained multi-objective problems in high-throughput experimentation platforms.
- C1[Low, Andre K. Y.; Vissol-Gaudin, Eleonore; Hippalgaonkar, Kedar] Nanyang Technol Univ, Sch Mat Sci & Engn, Singapore 639798, Singapore.
[Low, Andre K. Y.; Lim, Yee-Fun; Hippalgaonkar, Kedar] ASTAR, Inst Mat Res & Engn IMRE, 2 Fusionopolis Way,Innovis 08-03, Singapore 138634, Singapore.
[Mekki-Berrada, Flore; Ostudin, Aleksandr; Xie, Jiaxun; Khan, Saif A.] Natl Univ Singapore, Dept Chem & Biomol Engn, Singapore 117585, Singapore.
[Gupta, Abhishek] Indian Inst Technol Goa, Sch Mech Sci, Ponda 403401, Goa, India.
[Lim, Yee-Fun] ASTAR, Inst Sustainabil Chem Energy & Environm ISCE2, 1 Pesek Rd, Singapore 627833, Singapore.
[Li, Qianxiao] Natl Univ Singapore, Dept Math, Singapore 119077, Singapore.
[Li, Qianxiao] Natl Univ Singapore, Inst Funct Intelligent Mat, Singapore 117544, Singapore.
[Ong, Yew Soon] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore - C3Nanyang Technological University; Agency for Science Technology & Research (A*STAR); A*STAR - Institute of Materials Research & Engineering (IMRE); National University of Singapore; Indian Institute of Technology System (IIT System); Indian Institute of Technology (IIT) Goa; Agency for Science Technology & Research (A*STAR); National University of Singapore; National University of Singapore; Institute for Functional Intelligent Materials (I-FIM); Nanyang Technological University
- RPHippalgaonkar, K (corresponding author), Nanyang Technol Univ, Sch Mat Sci & Engn, Singapore 639798, Singapore; Hippalgaonkar, K (corresponding author), ASTAR, Inst Mat Res & Engn IMRE, 2 Fusionopolis Way,Innovis 08-03, Singapore 138634, Singapore; Khan, SA (corresponding author), Natl Univ Singapore, Dept Chem & Biomol Engn, Singapore 117585, Singapore
- FUAME Programmatic Funds by the Agency for Science, Technology and Research [A1898b0043, A20G9b0135]; National Research Foundation (NRF), Singapore [NRF- NRFF13-2021-0005]; The 25th NRF CRP programme [EDUNC-33-18-279-V12]; NRF fellowship [NRF-NRFF13-2021-0011]; Ministry of Education, Singapore
- FXThe authors acknowledge funding from AME Programmatic Funds by the Agency for Science, Technology and Research under Grant No. A1898b0043 and No. A20G9b0135. KH also acknowledges funding from the National Research Foundation (NRF), Singapore under the NRF Fellowship (NRF-NRFF13-2021-0011). SAK and FMB also acknowledge funding from the 25th NRF CRP programme (NRF-CRP25-2020RS-0002). QL also acknowledges support from the NRF fellowship (project No. NRF- NRFF13-2021-0005) and the Ministry of Education, Singapore, under its Research Centre of Excellence award to the Institute for Functional Intelligent Materials (I-FIM, project No. EDUNC-33-18-279-V12).
- NR51
- TC2
- Z92
- U17
- U27
- PUNATURE PORTFOLIO
- PIBERLIN
- PAHEIDELBERGER PLATZ 3, BERLIN, 14197, GERMANY
- J9NPJ COMPUT MATER
- JInpj Comput. Mater.
- PDMAY 13
- PY2024
- VL10
- DI10.1038/s41524-024-01274-x
- PG11
- WCChemistry, Physical; Materials Science, Multidisciplinary
- SCChemistry; Materials Science
- GAQN9T5
- UTWOS:001221677000002
- ER
- EF
|
Wu, Shiqi; Chamoin, Ludovic; Li, Qianxiao Non-intrusive model combination for learning dynamical systems PHYSICA D-NONLINEAR PHENOMENA, 463 , 2024, DOI: 10.1016/j.physd.2024.134152. Abstract | BibTeX | Endnote @article{ISI:001235225600001,
title = {Non-intrusive model combination for learning dynamical systems},
author = {Shiqi Wu and Ludovic Chamoin and Qianxiao Li},
doi = {10.1016/j.physd.2024.134152},
times_cited = {0},
issn = {0167-2789},
year = {2024},
date = {2024-04-27},
journal = {PHYSICA D-NONLINEAR PHENOMENA},
volume = {463},
publisher = {ELSEVIER},
address = {RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS},
abstract = {In data -driven modeling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of different fidelities, or hybrid models based on physical knowledge and data -driven strategies. A key limitation of the broad adoption of model combination in applications is intrusiveness: training combined models typically requires significant modifications to the learning algorithm implementations, which may often be already well -developed and optimized for individual model spaces. In this work, we propose an iterative, non -intrusive methodology to combine two model spaces to learn dynamics from data. We show that this can be understood, at least in the linear setting, as finding the optimal solution in the direct sum of the two hypothesis spaces, while leveraging only the projection operators in each individual space. Hence, the proposed algorithm can be viewed as iterative projections, for which we can obtain estimates on its convergence properties. To highlight the extensive applicability of our framework, we conduct numerical experiments in various problem settings, with particular emphasis on various hybrid models based on the Koopman operator approach.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In data -driven modeling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of different fidelities, or hybrid models based on physical knowledge and data -driven strategies. A key limitation of the broad adoption of model combination in applications is intrusiveness: training combined models typically requires significant modifications to the learning algorithm implementations, which may often be already well -developed and optimized for individual model spaces. In this work, we propose an iterative, non -intrusive methodology to combine two model spaces to learn dynamics from data. We show that this can be understood, at least in the linear setting, as finding the optimal solution in the direct sum of the two hypothesis spaces, while leveraging only the projection operators in each individual space. Hence, the proposed algorithm can be viewed as iterative projections, for which we can obtain estimates on its convergence properties. To highlight the extensive applicability of our framework, we conduct numerical experiments in various problem settings, with particular emphasis on various hybrid models based on the Koopman operator approach. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AUWu, SQ
Chamoin, L
Li, QX
- AFShiqi Wu
Ludovic Chamoin
Qianxiao Li
- TINon-intrusive model combination for learning dynamical systems
- SOPHYSICA D-NONLINEAR PHENOMENA
- LAEnglish
- DTArticle
- DELearning Dynamics; Model Combination; Machine Learning; Koopman Operator; Iterative Projection
- IDKOOPMAN OPERATOR
- ABIn data -driven modeling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of different fidelities, or hybrid models based on physical knowledge and data -driven strategies. A key limitation of the broad adoption of model combination in applications is intrusiveness: training combined models typically requires significant modifications to the learning algorithm implementations, which may often be already well -developed and optimized for individual model spaces. In this work, we propose an iterative, non -intrusive methodology to combine two model spaces to learn dynamics from data. We show that this can be understood, at least in the linear setting, as finding the optimal solution in the direct sum of the two hypothesis spaces, while leveraging only the projection operators in each individual space. Hence, the proposed algorithm can be viewed as iterative projections, for which we can obtain estimates on its convergence properties. To highlight the extensive applicability of our framework, we conduct numerical experiments in various problem settings, with particular emphasis on various hybrid models based on the Koopman operator approach.
- C3National University of Singapore; National University of Singapore; Institute for Functional Intelligent Materials (I-FIM); Centre National de la Recherche Scientifique (CNRS); Universite Paris Cite; Universite Paris Saclay; Institut Universitaire de France
- RPLi, QX (corresponding author), Natl Univ Singapore, Dept Math, Singapore 117543, Singapore; Li, QX (corresponding author), Natl Univ Singapore, Inst Funct Intelligent Mat, Singapore 117543, Singapore
- FXThis research is part of the programme DesCartes and is supported by the National Research Foundation, Prime Minister's Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.
- NR41
- TC0
- Z90
- U12
- U22
- PUELSEVIER
- PIAMSTERDAM
- PARADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS
- SN0167-2789
- J9PHYSICA D
- JIPhysica D
- PDJUL
- PY2024
- VL463
- DI10.1016/j.physd.2024.134152
- PG15
- WCMathematics, Applied; Physics, Fluids & Plasmas; Physics, Multidisciplinary; Physics, Mathematical
- SCMathematics; Physics
- GASN8P5
- UTWOS:001235225600001
- ER
- EF
|
Li, Qianxiao; Lin, Ting; Shen, Zuowei Deep Neural Network Approximation of Invariant Functions through Dynamical Systems JOURNAL OF MACHINE LEARNING RESEARCH, 25 , 2024. Abstract | BibTeX | Endnote @article{ISI:001335023200001,
title = {Deep Neural Network Approximation of Invariant Functions through Dynamical Systems},
author = {Qianxiao Li and Ting Lin and Zuowei Shen},
times_cited = {0},
issn = {1532-4435},
year = {2024},
date = {2024-01-01},
journal = {JOURNAL OF MACHINE LEARNING RESEARCH},
volume = {25},
publisher = {MICROTOME PUBL},
address = {31 GIBBS ST, BROOKLINE, MA 02446 USA},
abstract = {We study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems. Such invariant functions include the much studied translation-invariant ones involving image tasks, but also encompasses many permutation-invariant functions that find emerging applications in science and engineering. We prove sufficient conditions for universal approximation of these functions by a controlled dynamical system, which can be viewed as a general abstraction of deep residual networks with symmetry constraints. These results not only imply the universal approximation for a variety of commonly employed neural network architectures for symmetric function approximation, but also guide the design of architectures with approximation guarantees for applications involving new symmetry requirements.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems. Such invariant functions include the much studied translation-invariant ones involving image tasks, but also encompasses many permutation-invariant functions that find emerging applications in science and engineering. We prove sufficient conditions for universal approximation of these functions by a controlled dynamical system, which can be viewed as a general abstraction of deep residual networks with symmetry constraints. These results not only imply the universal approximation for a variety of commonly employed neural network architectures for symmetric function approximation, but also guide the design of architectures with approximation guarantees for applications involving new symmetry requirements. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AULi, QX
Lin, T
Shen, ZW
- AFQianxiao Li
Ting Lin
Zuowei Shen
- TIDeep Neural Network Approximation of Invariant Functions through Dynamical Systems
- SOJOURNAL OF MACHINE LEARNING RESEARCH
- LAEnglish
- DTArticle
- DEDeep Learning; Approximation Theory; Dynamical Systems; Control; Invariance
- IDWIDTH
- ABWe study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems. Such invariant functions include the much studied translation-invariant ones involving image tasks, but also encompasses many permutation-invariant functions that find emerging applications in science and engineering. We prove sufficient conditions for universal approximation of these functions by a controlled dynamical system, which can be viewed as a general abstraction of deep residual networks with symmetry constraints. These results not only imply the universal approximation for a variety of commonly employed neural network architectures for symmetric function approximation, but also guide the design of architectures with approximation guarantees for applications involving new symmetry requirements.
- C1[Li, Qianxiao; Lin, Ting] Natl Univ Singapore, Dept Math, Inst Funct Intelligent Mat, 10 Lower Kent Ridge Rd, Singapore 119076, Singapore.
[Shen, Zuowei] Peking Univ, Sch Math Sci, 5 Yiheyuan Rd, Beijing 100871, Peoples R China.
[Shen, Zuowei] Natl Univ Singapore, Dept Math, 10 Lower Kent Ridge Rd, Singapore 119076, Singapore - C3Institute for Functional Intelligent Materials (I-FIM); National University of Singapore; Peking University; National University of Singapore
- RPLi, QX (corresponding author), Natl Univ Singapore, Dept Math, Inst Funct Intelligent Mat, 10 Lower Kent Ridge Rd, Singapore 119076, Singapore
- FUNational Research Foundation, Singapore under the NRF fellowship [NRF-NRFF13-2021-0005]; Elite Program of Computational and Applied Mathematics for PhD Candidates in Peking University; Distinguished Professorship of National University of Singapore
- FXWe are grateful for discussions with Isaac P. S. Tian and Tonio Buonassisi on the applications of the theory developed to materials modelling. Q.L. is supported by the National Research Foundation, Singapore under the NRF fellowship (project No. NRF-NRFF13-2021-0005) . T.L. is partially supported by The Elite Program of Computational and Applied Mathematics for PhD Candidates in Peking University. Z.S. is supported under the Distinguished Professorship of National University of Singapore.
- NR47
- TC0
- Z90
- U10
- U20
- PUMICROTOME PUBL
- PIBROOKLINE
- PA31 GIBBS ST, BROOKLINE, MA 02446 USA
- SN1532-4435
- J9J MACH LEARN RES
- JIJ. Mach. Learn. Res.
- PY2024
- VL25
- PG57
- WCAutomation & Control Systems; Computer Science, Artificial Intelligence
- SCAutomation & Control Systems; Computer Science
- UTWOS:001335023200001
- ER
- EF
|
