Tyler Maunu

About Me

I am an Assistant Professor of Mathematics at Brandeis University. In 2018, I obtained my PhD in Mathematics and MS in Statistics at the University of Minnesota, and from 2018-2021 I was an Instructor in Applied Mathematics at MIT. My current research interests span statistics, machine learning, computer vision, and nonconvex optimization. In the past, I have specifically focused on the problem of robust subspace recovery and more recently I have been interested in problems related to optimal transport.

Publications

• Tyler Maunu and Martin Molina-Fructuoso. "Acceleration and Implicit Regularization in Gaussian Phase Retrieval." International Conference on Artificial Intelligence and Statistics. PMLR, 2024.[PDF]
• Tyler Maunu. First-Order Algorithms for Optimization over Graph Laplacians. Sampling Theory and Applications (SampTA). 2023.[PDF]
• Tyler Maunu, Thibaut Le Gouic, and Philippe Rigollet. Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery. International Conference on Artificial Intelligence and Statistics (AISTATS). 2023.[PDF]
• Tyler Maunu and Gilad Lerman, Depth Descent Synchronization in SO(D). International Journal of Computer Vision. 2023.[PDF]
• Tyler Maunu, Chenyu Yu, and Gilad Lerman. Stochastic and Private Nonconvex Outlier-Robust PCA. Mathematical and Scientific Machine Learning (2022).[PDF]
• Max Daniels, Tyler Maunu and Paul Hand, Score-based Generative Neural Networks for Large-Scale Optimal Transport. Advances in Neural Information Processing Systems (NeurIPS). 2021.[PDF]
• Yunpeng Shi, Shaohan Li, Tyler Maunu and Gilad Lerman, Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching. International Conference on 3D Vision. 2021.[PDF]
• Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence. Advances in Neural Information Processing Systems (NeurIPS). 2020.[PDF]
• Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, Austin Stromme, Exponential ergodicity of mirror Langevin diffusions. Advances in Neural Information Processing Systems (NeurIPS). 2020. [PDF]
• Sinho Chewi, Tyler Maunu, Philippe Rigollet, and Austin Stromme, Gradient Descent Algorithms for Bures-Wasserstein Barycenters. Conference on Learning Theory (COLT). 2020. [PDF]
• Tyler Maunu and Gilad Lerman, Robust Subspace Recovery with Adversarial Outliers. 2019.[PDF]
• Tyler Maunu, Teng Zhang, and Gilad Lerman, A Well-Tempered Landscape for Non-convex Robust Subspace Recovery. Journal of Machine Learning Research, 2019.[PDF] 
• Gilad Lerman and Tyler Maunu, An Overview of Robust Subspace Recovery, Proceedings of the IEEE, 2018.[PDF] 
• Gilad Lerman and Tyler Maunu, Fast, Robust and Non-convex Subspace Recovery, Information and Inference: A Journal of the IMA, 2017.[PDF]

Teaching

F24: MATH 124A: Optimization.

Code

Contact Information

Email: maunu@brandeis.edu

Office: Goldsmith 313