About me

I am a Postdoc at Mila-Quebec AI Institute. I am working with groups of Guy Wolf (Mila), Smita Krishnaswamy (Krishnaswamy Lab, Yale University) and Bastian Rieck (AIDOS, Helmholtz Munich). I received my Ph.D. in Mathematics from Queen's University under the supervision of Professor Andrew Lewis.

My current research mainly focus on developing novel machine learning methodology using tools from pure mathematical theory and applying to biomedical discovery through analyzing complex data from real world, thus bridging the gap between the rigorous abstractions of pure mathematics and the practical, data-driven challenges posed by biological and data science questions.

My previous research focused on geometric analysis and its applications to geometric control theory. More specifically, I worked on the development of an exponential map from the Lie algebra of time-varying vector fields to the groupoid of diffeomorphisms with various degrees of regularity. This work combines geometric, topological, and algebraic methods and can be applied to problems in geometric control theory. I was also engaged in works in fixed point theory and nonlinear spectral theory collaborated with people from other universities.

My research interests include machine learning, computational biology, geometric analysis.

Publications & Preprints

* denotes equal contribution

Lewis, A., and Zhang, Y., ''Topologies for geometric flows and continuous dependence on parameters'', (Submitted to EJDE), 2023. (pdf)

Bhaskar*, D., Zhang*, Y., Xu*, C., Sun, X., Fasina, O., Wolf, G., Nickel, M., Perlmutter, M., and Krishnaswamy, "Graph Topological Property Recovery with Heat and Wave Dynamics-based Features on Graphs" (submitted to ICASSP), 2023. (pdf)

Fasina, O., Huguet, G., Tong, A., Zhang, Y., Wolf, G., Nickel, M., Adelstein, I., and Krishnaswamy, S., "Neural FIM for learning Fisher information metrics from point cloud data", International Conference on Machine Learning (ICML), 2023. (pdf)

Huguet, G., Tong, A., Brouwer, E. D., Zhang, Y., Wolf, G., Adelstein, I., and Krishnaswamy, S., "A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction", Neural Information Processing Systems (NeurIPS), 2023. (pdf)

Tong, A., Malkin, N., Fatras, K., Atanackovic, L., Zhang, Y., Huguet, G., Wolf, G., and Bengio, Y., "Simulation-free Schrödinger bridges via score and flow matching", Presented in Frontiers4LCD Workshop @ ICML (submitted to NeurIPS), 2023. (pdf)

Tong, A., Malkin, N., Huguet, G., Zhang, Y., Rector-Brooks, J., FATRAS, K., Wolf, G., and Bengio, Y., "Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport", Presented in Frontiers4LCD Workshop @ ICML (submitted to NeurIPS), 2023. (pdf)
Tong, A., Malkin, N., Huguet, G., Zhang, Y., Rector-Brooks, J., FATRAS, K., Wolf, G., and Bengio, Y., "Conditional Flow Matching: Simulation-Free Dynamic Optimal Transport", (ArXiv), 2023.