Marios Mattheakis (Matthaiakis)

About

I am a Machine Learning Research Engineer specializing in scientific computing and complex systems. I was previously a researcher at Harvard University, where I worked on AI-driven scientific computing projects. My academic foundation is a Ph.D. in computational physics (University of Crete, 2014).

My work focuses on physics-based models and neural operators—building custom neural networks and surrogate models that embed physical principles and symmetries to boost data efficiency and accuracy. I apply these methods in areas like fluid dynamics, materials, and engineering. Ultimately, I aim to advance AI-driven scientific computing and tackle real-world challenges.

Curriculum Vitae  ·  Resume  ·  Google Scholar  ·  dblp  ·  Semantic Scholar  ·  ORCID

Appointments

2024–present: Machine Learning Research Engineer at APQX

2022–2024: Senior Scientist at the Deep Learning Center of E Ink Corporation

2018–2022: Research Associate, Institute for Applied Computational Science at Harvard 

2015–2018:  Postdoctoral Researcher, Harvard John A. Paulson School of Engineering and Applied Sciences

Publications

2024

Ariel Norambuena, Marios Mattheakis, Francisco J. Gonzalez, and Raul Coto. “Physics-informed neural networks for quantum control.” Phys. Rev. Lett., 132,  010801 (2024)
Article

Circe Hsu, Marios Mattheakis, Gabriel R Schleder, and Daniel T. Larson. 2024. “Equation-driven Neural Networks for Periodic Quantum Systems.” In NeurIPS Workshop on Machine Learning and Physical Sciences.
PDF

2023

Ziyan Zhu, Marios Mattheakis, Weiwei Pan, and Efthimios Kaxiras. 2023. “HubbardNet: Efficient Predictions of the Bose-Hubbard Model Spectrum with Deep Neural Networks.” Phys. Rev. Research , 5, pp. 043084.
Article  |  arXiv  |  PDF (preprint)

Trevor David Rhone, Romakanta Bhattarai, Haralambos Gavras, Bethany Lusch, Misha Salim, Marios Mattheakis, Daniel T. Larson, Yoshiharu Krockenberger, and Efthimios Kaxiras. 2023. “Artificial intelligence guided studies of van der Waals magnets.” Advanced Theory and Simulations, pp. 2300019.
Article

Marios Mattheakis, Hayden Joy, and Pavlos Protopapas. 2023. “Unsupervised Reservoir Computing for Solving Ordinary Differential Equations.” International Journal on Artificial Intelligence Tools, 32, 1.
Article  |  arXiv  |  PDF (preprint)

2022

Marios Mattheakis, David Sondak, Akshunna S. Dogra, and Pavlos Protopapas. 2022. “Hamiltonian neural networks for solving equations of motion.” Phys. Rev. E, 105, pp. 065305.
Article  |  arXiv  |  PDF (preprint)

Shaan Desai, Marios Mattheakis, Hayden Joy, Pavlos Protopapas, and Stephen Roberts. 2022. “One-Shot Transfer Learning of Physics-Informed Neural Networks.” In ICML, workshop AI4Science.
arXiv  |  PDF (preprint)

Mattia Angelia, Georgios Neofotistos, Marios Mattheakis, and Efthimios Kaxiras. 2022. “Modeling the effect of the vaccination campaign on the Covid-19 pandemic.” Chaos, Solitons and Fractals, 154, pp. 111621.
Article  |  arXiv  |  PDF (preprint)

Anwesh Bhattacharya, Marios Mattheakis, and Pavlos Protopapas. 2022. “Encoding Involutory Invariance in Neural Networks.” In IJCNN at IEEE World Congress on Computational Intelligence.
arXiv  |  PDF (preprint)

Marios Mattheakis, Gabriel R. Schleder, Daniel T. Larson, and Efthimios Kaxiras. 2022. “First principles physics-informed neural network for quantum wavefunctions and eigenvalue surfaces.” In NeurIPS Workshop on Machine Learning and Physical Sciences.
arXiv  |  PDF (preprint)

Ziyan Zhu, Marios Mattheakis, Weiwei Pan, and Efthimios Kaxiras. 2022. “HubbardNet: Efficient Predictions of the Bose-Hubbard Model Spectrum with Deep Neural Networks.” In NeurIPS Workshop on Machine Learning and Physical Sciences.
arXiv  |  PDF (preprint)

Henry Jin, Marios Mattheakis, and Pavlos Protopapas. 2022. “Physics-Informed Neural Networks for Quantum Eigenvalue Problems.” In IJCNN at IEEE World Congress on Computational Intelligence.
arXiv  |  PDF (preprint)

Hayden Joy, Marios Mattheakis, and Pavlos Protopapas. 2022. “RcTorch: a PyTorch Reservoir Computing Package with Automated Hyper-Parameter Optimization.” arXiv paper.
arXiv  |  PDF (preprint)

Raphael Pellegrin, Blake Bullwinkel, Marios Mattheakis, and Pavlos Protopapas. 2022. “Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows.” In NeurIPS Workshop on Machine Learning and Physical Sciences.
PDF

2021

Shaan Desai, Marios Mattheakis, David Sondak, Pavlos Protopapas, and Stephen Roberts. 2021. “Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems.” Phys. Rev. E, 104, pp. 034312.
Article  |  arXiv  |  PDF (preprint)

Shaan Desai, Marios Mattheakis, and Stephen Roberts. 2021. “Variational Integrator Graph Networks for Learning Energy Conserving Dynamical Systems.” Phys. Rev. E, 104, pp. 035310.
Article  |  arXiv  |  PDF (preprint)

Tiago A. E. Ferreira, Marios Mattheakis, and Pavlos Protopapas. 2021. “A New Artificial Neuron Proposal with Trainable Simultaneous Local and Global Activation Function.”
arXiv  |  PDF (preprint)

2020

Alessandro Paticchio, Tommaso Scarlatti, Marios Mattheakis, Pavlos Protopapas, and Marco Brambilla. 2020. “Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread.” In 2020 NeurIPS Workshop on Machine Learning and the Physical Sciences. NeurIPS.
arXiv  |  PDF (preprint)

Henry Jin, Marios Mattheakis, and Pavlos Protopapas. 2020. “Unsupervised Neural Networks for Quantum Eigenvalue Problems.” In 2020 NeurIPS Workshop on Machine Learning and the Physical Sciences. NeurIPS.
arXiv  |  PDF (preprint)

Marios Mattheakis. 2020. “Riding Waves in Neuromorphic Computing.” Physics 13, 132, pp. 1-3.
Article  |  PDF

Yue Luo, Rebecca Engelke, Marios Mattheakis, Michele Tamagnone, Stephen Carr, Kenji Watanabe, Takashi Taniguchi, Efthimios Kaxiras, Philip Kim, and William L. Wilson. 2020. “In-situ nanoscale imaging of moiré superlattices in twisted van der Waals heterostructures.” Nature Communications, 11, 4209, pp. 1-7.
Article  |  PDF

G. A. Tritsaris, S. Carr, Z. Zhu, Y. Xie, S. Torrisi, J. Tang, M. Mattheakis, D. Larson, and E. Kaxiras. 2020. “Electronic structure calculations of twisted multi-layer graphene superlattices.” 2D Materials, 7, pp. 035028.
Article  |  arXiv  |  PDF (preprint)

Georgios A. Tritsaris, Yiqi Xie, Alexander M. Rush, Stephen Carr, Marios Mattheakis, and Efthimios Kaxiras. 2020. “LAN -- A materials notation for 2D layered assemblies.” J. Chem. Inf. Model.
Article  |  arXiv  |  PDF (preprint)

Feiyu Chen, David Sondak, Pavlos Protopapas, Marios Mattheakis, Shuheng Liu, Devansh Agarwal, and Marco Di Giovanni. 2020. “NeuroDiffEq: A Python package for solving differential equations with neural networks.” Journal of Open Source Software, 5, 46.
Article  |  PDF

G. Barmparis, G. Neofotistos, M. Mattheakis, J. Hitzanidi, G. P. Tsironis, and E. Kaxiras. 2020. “Robust prediction of complex spatiotemporal states through machine learning with sparse sensing.” Physics Letters A, 384, pp. 126300.
Article

2019

M. Maier, M. Mattheakis, E. Kaxiras, M. Luskin, and D. Margetis. 2019. “Homogenization of plasmonic crystals: Seeking the epsilon-near-zero behavior.” Proceedings of the Royal Society A, 475, 2230.
Article  |  arXiv  |  PDF (preprint)

Marios Mattheakis, Matthias Maier, Wei Xi Boo, and Efthimios Kaxiras. 2019. “Graphene epsilon-near-zero plasmonic crystals.” In NANOCOM '19 Proceedings of the Sixth Annual ACM International Conference on Nanoscale Computing and Communication. Dublin, Ireland.
Article  |  arXiv  |  PDF (preprint)

M. Mattheakis, P. Protopapas, D. Sondak, M. Di Giovanni, and E. Kaxiras. 2019. “Physical Symmetries Embedded in Neural Networks.” arXiv paper, 1904.08991.
arXiv  |  PDF (preprint)

G. N. Neofotistos, M. Mattheakis, G. Barmparis, J. Hitzanidi, G. P. Tsironis, and E. Kaxiras. 2019. “Machine learning with observers predicts complex spatiotemporal behavior.” Front. Phys. - Quantum Computing , 7, 24, pp. 1-9.
Article  |  arXiv  |  PDF (preprint)

2018

Najm Hassan, Marios Mattheakis, and Ming Ding. 2018. “Sensorless Node Architecture for Events Detection in Self-Powered Nanosensor Networks.” Nano Communication Networks, 19, pp. 1-9.
Article

Marios Mattheakis, G. P. Tsironis, and Efthimios Kaxiras. 2018. “Emergence and dynamical properties of stochastic branching in the electronic flows of disordered Dirac solids.” EPL, 122, pp. 27003.
Article  |  arXiv  |  PDF (preprint)

Sharmila N. Shirodkar, Marios Mattheakis, Paul Cazeaux, Prineha Narang, Marin Soljačić, and Efthimios Kaxiras. 2018. “Quantum plasmons with optical-range frequencies in doped few-layer graphene.” Phys. Rev. B, 97, pp. 195435.
Article  |  arXiv  |  PDF (preprint)

Matthias Maier, Marios Mattheakis, Efthimios Kaxiras, Mitchell Luskin, and Dionisios Margetis. 2018. “Universal behavior of dispersive Dirac cone in gradient-index plasmonic metamaterials.” Phys. Rev. B, 97, 3, pp. 035307.
Article  |  arXiv  |  PDF (preprint)

2017

M. Mattheakis, G. P. Tsironis, and E. Kaxiras. 2017. “Graphene and Active Metamaterials: Theoretical Methods and Physical Properties.” In Nanoplasmonics - Fundamentals and Applications, edited by Gregory Barbillon. InTech.
Article  |  arXiv  |  PDF (preprint)

O. V. Shramkova, Marios Mattheakis, and G. P. Tsironis. 2017. “Amplification of surface plasmons in active nonlinear hyperbolic systems.” In 47th European Microwave Conference (EuMC), pp. 488-491. Nuremberg, Germany.
Article

Constantinos A. Valagiannopoulos, Marios Mattheakis, Sharmila N. Shirodkar, and Efthimios Kaxiras. 2017. “Manipulating polarized light with a planar slab of Black Phosphorus.” Journal of Physics Communications, 1, pp. 045003.
Article  |  arXiv  |  PDF (preprint)

2016

M. Mattheakis, C. A. Valagiannopoulos, and E. Kaxiras. 2016. “Epsilon-Near-Zero behavior from Plasmonic Dirac Point: theory and realization using two-dimensional materials.” Physical Review B, 94, 20, pp. 201404(R).
Article  |  arXiv  |  PDF (preprint)

M. Mattheakis, I. J. Pitsios, G. P. Tsironis, and S. Tzortzakis. 2016. “Extreme events in complex linear and nonlinear photonic media.” Chaos, Solitons & Fractals, 84, pp. 73-80.
Article  |  arXiv  |  PDF (preprint)

M. Mattheakis, T. Oikonomou, Μ Molina, and G. P. Tsironis. 2016. “Phase transition in PT symmetric active plasmonic systems.” IEEE Journal of Selected Topics in Quantum Electronics, 22, 5, pp. 1-7.
Article  |  arXiv  |  PDF (preprint)

2015

M. Mattheakis and G. P. Tsironis. 2015. “Extreme waves and branching flows in optical media.” In Quodons in Mica: Nonlinear localized travelling excitations in crystals , 221: pp. 425-454. Springer.
Article  |  arXiv  |  PDF (preprint)

2014

Marios Mattheakis. 2014. “Electromagnetic wave propagation in gradient index metamaterials, plasmonic systems and optical fiber networks.” University of Crete, Department of Physics.
Thesis record

C. Athanasopoulos, M. Mattheakis, and G. P. Tsironis. 2014. “Enhanced surface plasmon polariton propagation induced by active dielectrics.” In Proceedings of the 2014 COMSOL Conference in Cambridge. Cambridge, UK: COMSOL.
Article  |  arXiv  |  PDF

F. Perakis, M. Mattheakis, and G. P. Tsironis. 2014. “Small-world networks of optical fiber lattices.” Journal of Optics, 16, pp. 102003.
Article  |  arXiv  |  PDF (preprint)

2012

M. Mattheakis, G. P. Tsironis, and V. I. Kovanis. 2012. “Luneburg lens waveguide networks.” Journal of Optics, 14, pp. 114006.
Article  |  arXiv  |  PDF (preprint)