M

Michael Scherbela

I’m a machine learning researcher with a background in physics and management consulting. I enjoy technology, working with great people, and being outdoors.

hero image

Education and Research

Present

University of Vienna

· Vienna, Austria

PhD: Mathematics / Machine Learning

Using deep-learning to develop new ab-initio methods for quantum chemistry

Oct 2020
Jun 2017

Graz University of Technology

· Graz, Austria

Master: Physics

Studying physics with a focus on computational methods. Master thesis on using machine learning to predict surface structures of molecules adsorbing to metal surfaces. Graduated with distinction.

Dec 2014
Nov 2014

Graz University of Technology

· Graz, Austria

Bachelor: Physics

Studying physics and graduating with a bachelor thesis on using Matrix Product States to simulate quantum spin systems. Graduated with distinction.

Oct 2011

Work Experience

Oct 2020

McKinsey & Co

· Europe

Consultant

Top-management consulting for a diverse set of clients across Europe, focusing on data- and technology-driven projects

Apr 2018
Feb 2016

Virtual Vehicle Research Center

· Graz, Austria

Student Researcher

Experimental and computational research to improve automotive systems

Feb 2013
Aug 2017

Infineon Technologies

· Graz, Austria

Summer Internship

Automating testing of semiconductor devices during development

Jul 2017
Oct 2012

SLR Engineering Technologies

· Graz, Austria

Working Student

Software development for image recognition in traffic control applications

Jul 2011
Aug 2011

Anton Paar

· Graz, Austria

Summer Internship

Assembly of high precision density measurement devices

Aug 2011

Research Highlights

I work on the intersection of machine learning and quantum chemistry. A full and up to date list of my publications can be found on Google Scholar .

Scientific papers

YearTitleAuthorsJournal
2023Variational Monte Carlo on a Budget - Fine-tuning pre-trained Neural WavefunctionsScherbela, Gerard, GrohsNeurIPS 2023
2023Towards a Transferable Fermionic Neural Wavefunction for MoleculesScherbela, Gerard, GrohsNature Communications
2022Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networksScherbela, Reisenhofer, Gerard, Grohs, MarquetandNature Computational Science
2022Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?Gerard, Scherbela, Grohs, MarquetandNeurIPS 2022
2020Charge Transfer into Organic Thin Films: A Deeper Insight through Machine‐Learning‐Assisted Structure SearchEgger, Hörmann, Jeindl, Scherbela, Obersteiner, Todorovic, Rinke, HofmannAdvanced Science
2019SAMPLE: Surface structure search enabled by coarse graining and statistical learningHörmann, Jeindl, Egger, Scherbela, HofmannComputer Physics Communications
2018Charting the energy landscape of metal/organic interfaces via machine learningScherbela, Hörmann, Jeindl, Obersteiner, HofmannPhysical Review Materials
2017Structure prediction for surface-induced phases of organic monolayers: overcoming the combinatorial bottleneckObersteiner, Scherbela, Hörmann, Wegner, HofmannNano Letters

Presentations

YearTypeTitleVenueLink
2022Invited TalkHigh accuracy wavefunctions using deep-learning-based variational Monte CarloIPAM, UC Los AngelesRecording on youtube
2022Summer School TutorialBasics of Machine LearningErwin Schrödinger Institute, ViennaMaterial on GitHub
2021Poster PresentationSharing is Caring: Accurate ab-initio wavefunctions through weight-sharing neural networksEPFL, LausanneCorresponding paper
2017TalkStructure Search using Machine LearningDPG Spring Meeting, Dresden
2017TalkStructure Search at Interfaces using Bayesian RegressionIMPRESS Conference 2017, Helsinki

Personal projects

I enjoy working on small side projects. Some of them are silly, but I’ve learned a lot from all of them. Here are a few which I particularly enjoy.


Get in touch

email icon github icon twitter icon google scholar icon linkedin icon