Dr Tiffany Vlaar

  • Lecturer in Applied Mathematics (Mathematics)

Biography

I am an ELLIS (European Laboratory for Learning and Intelligent Systems) Member. Prior to becoming a lecturer at the University of Glasgow, I was a postdoctoral researcher at Mila - Quebec AI Institute and McGill University in climate change AI and mathematics of deep learning. I obtained my Mathematics PhD from the University of Edinburgh, during which I was a Turing Enrichment student, and also have a background in physics (MSc, Perimeter Institute).

Pronouns: she/her.

Research interests

See website for more info on research projects: tiffanyvlaar.github.io

Research groups

Publications

List by: Type | Date

Jump to: 2024 | 2022 | 2021 | 2019 | 2016
Number of items: 6.

2024

Müller, M., Vlaar, T. , Rolnick, D. and Hein, M. (2024) Normalization Layers Are All That Sharpness-Aware Minimization Needs. In: 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, Louisiana, USA, 10-16 December 2023,

2022

Vlaar, T. and Leimkuhler, B. (2022) Multirate Training of Neural Networks. In: 39th International Conference on Machine Learning (ICML2022), Baltimore, Maryland, USA, 17-23 July 2022, pp. 22342-22360.

Vlaar, T. J. and Frankle, J. (2022) What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? In: 39th International Conference on Machine Learning (ICML2022), Baltimore, Maryland, USA, 17-23 July 2022, pp. 22325-22341.

2021

Leimkuhler, B., Vlaar, T. , Pouchon, T. and Storkey, A. (2021) Better Training using Weight-Constrained Stochastic Dynamics. In: 38th International Conference on Machine Learning (ICML2021), 18-24 July 2022, pp. 6200-6211.

2019

Leimkuhler, B., Matthews, C. and Vlaar, T. (2019) Partitioned integrators for thermodynamic parameterization of neural networks. Foundations of Data Science, 1(4), pp. 457-489. (doi: 10.3934/fods.2019019)

2016

Chojnacki, L., Cook, C. Q., Dalidovich, D., Hayward Sierens, L. E., Lantagne-Hurtubise, É., Melko, R. G. and Vlaar, T. J. (2016) Shape dependence of two-cylinder Rényi entropies for free bosons on a lattice. Physical Review B, 94(16), 165136. (doi: 10.1103/PhysRevB.94.165136)

This list was generated on Tue Jan 21 04:04:15 2025 GMT.
Jump to: Articles | Conference Proceedings
Number of items: 6.

Articles

Leimkuhler, B., Matthews, C. and Vlaar, T. (2019) Partitioned integrators for thermodynamic parameterization of neural networks. Foundations of Data Science, 1(4), pp. 457-489. (doi: 10.3934/fods.2019019)

Chojnacki, L., Cook, C. Q., Dalidovich, D., Hayward Sierens, L. E., Lantagne-Hurtubise, É., Melko, R. G. and Vlaar, T. J. (2016) Shape dependence of two-cylinder Rényi entropies for free bosons on a lattice. Physical Review B, 94(16), 165136. (doi: 10.1103/PhysRevB.94.165136)

Conference Proceedings

Müller, M., Vlaar, T. , Rolnick, D. and Hein, M. (2024) Normalization Layers Are All That Sharpness-Aware Minimization Needs. In: 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, Louisiana, USA, 10-16 December 2023,

Vlaar, T. and Leimkuhler, B. (2022) Multirate Training of Neural Networks. In: 39th International Conference on Machine Learning (ICML2022), Baltimore, Maryland, USA, 17-23 July 2022, pp. 22342-22360.

Vlaar, T. J. and Frankle, J. (2022) What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? In: 39th International Conference on Machine Learning (ICML2022), Baltimore, Maryland, USA, 17-23 July 2022, pp. 22325-22341.

Leimkuhler, B., Vlaar, T. , Pouchon, T. and Storkey, A. (2021) Better Training using Weight-Constrained Stochastic Dynamics. In: 38th International Conference on Machine Learning (ICML2021), 18-24 July 2022, pp. 6200-6211.

This list was generated on Tue Jan 21 04:04:15 2025 GMT.

Supervision

If you are interested in my research, please feel free to reach out to me to discuss PhD options at the University of Glasgow.
In your email please include your CV, university transcripts, and any dissertations/papers you may have written (but do not worry if you do not have any publications at this stage).

  • Funding is available, but competitive, and requires going through the School’s application process. More information on the application process can be found here and more info on the project Dissecting Neural Networks can be found on the FindAPhD page 
    Shortlisting starts early January, and continues until all funded places are awarded.

  • The University of Glasgow also offers James McCune Smith scholarships for black UK domiciled students. More information: https://www.gla.ac.uk/scholarships/mccune-smith/

  • Further, I am a PhD supervisor within the DiveIn CDT. This CDT prioritises diversity and aims to produce transformative interdisciplinary research in various areas, including Net Zero and AI.
    It offers fully funded four-year interdisciplinary PhDs starting in September 2025.
    Applications due: 31 January 2025.
    More information: DiveIn CDT and my supervisor profile
    Please reach out to me if you are interested in applying for this opportunity.

  • I will be supervising a project on Deep Learning Optimization and Design Choices for Marine Biodiversity Monitoring with Dr. De Clippele (University of Glasgow) within the Leverhulme Programme for Doctoral Training in Ecological Data Science. More info will become available soon on: https://ecological-data-science.github.io

  • I am a co-supervisor on the marine rewilding effect project with Dr. De Clippele (main, University of Glasgow), Dr. Hogdson (CreditNature), and Dr. Wartmann (University of Aberdeen) within the NETGAIN CDT. Applications due: 31 January 2025.
    More information will become available on: https://netgain.wp.st-andrews.ac.uk 

  • I am a co-supervisor on the Developing GPU-accelerated digital twins of ecological systems for population monitoring and scenario analyses project with Prof. Torney (main, University of Glasgow), Prof. Morales (University of Glasgow), Prof. McCrea (Lancaster University), and Prof. Husmeier (University of Glasgow) within the ExaGEO CDT. Applications due: 17 February 2025. All info available on: https://www.exageo.org

 

If you are an UG student in the University of Aberdeen, Edinburgh, Glasgow, Heriot-Watt, or St Andrews, consider applying for my UG Summer Research project. Topic: Monitoring vegetation patterns from drone imagery using machine learning. Co-supervisor: Dr. Eizenhöfer (School of Geographical & Earth Sciences, University of Glasgow). Deadline: 13 January.

 

Teaching

Mathematics 1G: Introduction to Algebra, Geometry & Networks (MATHS1016).

Large-Scale Computing for Data Analytics (STATS5083), University of Glasgow, 2025.

Additional information

I'm a board member of the One World Seminar on Mathematics of Machine Learning (https://www.oneworldml.org/), come along to the talks if you’re interested!

I am also an organizer of the Network on Mathematical Data Science for Materials Science. 

I am passionate about increasing diversity in postgraduate research programmes in STEM. I am General Chair of the Women in Machine Learning (WiML) workshop at NeurIPS 2024. I co-founded the Piscopia Initiative (piscopia.co.uk) to provide information about how to apply to PhDs and what doing a PhD is like. The events are particularly aimed at women and non-binary people in Mathematics, but anyone is welcome to attend. Check out the https://piscopia.co.uk/contacts/ section for info on related initiatives. 


Tiffany Vlaar