Siamak Ravanbakhsh
About
Appointed Canada CIFAR AI Chair – 2019
Siamak Ravanbaksh is a Canada CIFAR AI Chair at Mila and an assistant professor at McGill University’s School of Computer Science.
Ravanbakhsh’s research area is machine learning. His broad interests lie in the problem of representation learning and inference in structured, complex, and combinatorial domains. His current research focuses on the role of invariance and symmetry in deep representation learning.
Relevant Publications
- Akhound-Sadegh, T., Perreault-Levasseur, L., Brandstetter, J., Welling, M., & Ravanbakhsh, S. (2024). Lie point symmetry and physics-informed networks. Advances in Neural Information Processing Systems.
- Jain, V., & Ravanbakhsh, S. (2024). Learning to Reach Goals via Diffusion. International Conference on Machine Learning .
- Kaba, S.O., Mondal, A.K., Zhang, Y., Bengio, Y., & Ravanbakhsh, S. (2023). Equivariance with learned canonicalization functions. International Conference on Machine Learning.
- Shakerinava, M., Mondal, A. K., & Ravanbakhsh, S. (2022). Structuring representations using group invariants. Advances in Neural Information Processing Systems.
- Kaba, S. O., & Ravanbakhsh, S. (2022) Equivariant Networks for Crystal Structures. Advances in Neural Information Processing Systems.