Matt Jordan

I am fifth-year PhD student in the department of Computer Science at the University of Texas at Austin advised by Alex Dimakis . I am broadly interested in the theoretical underpinnings of machine learning with guarantees, focusing on adversarial robustness and certification. I am also interested in ReLU geometry and algorithmic fairness. Prior to this, I received my bachelors degree form MIT majoring in computer science and theoretical mathematics.

Publications

	Inverse Problems Leveraging Pre-trained Contrastive Representations Sriram Ravula, Georgios Smyrnis, Matt Jordan, Alexandros G. Dimakis Advances in Neural Information Processing Systems (NeurIPS) 2021. [PDF]   [Code]
	Provable Lipschitz Certification for Generative Models Matt Jordan, Alexandros G. Dimakis International Conference on Machine Learning (ICML) 2021. [PDF]   [Code]
	Quarantines as a Targeted Immunization Strategy Jessica Hoffmann, Matt Jordan, Constantine Caramanis. Preprint, arXiv:2008.08262. [PDF]
	Exactly Computing the Local Lipschitz Constant of ReLU Networks Matt Jordan, Alexandros G. Dimakis. Advances in Neural Information Processing Systems (NeurIPS) 2020. [PDF]   [Code]
	Provable Certificates for Adversarial Examples: Fitting a Ball in a Union of Polytopes Matt Jordan, Justin Lewis, Alexandros G. Dimakis. Advances in Neural Information Processing Systems (NeurIPS) 2019. [PDF]   [Code]   [Talk]
	Quantifying Perceptual Distortion of Adversarial Examples Matt Jordan, Naren Manoj, Surbhi Goel, Alexandros G. Dimakis. Preprint, arXiv:1902.08265. [PDF]   [Code]