Paris Giampouras

Assistant Professor @ Department of Computer Science, University of Warwick.

prof_pic.jpg

CS2.31,Dep. of Computer Science

University of Warwick,

Coventry

CV4 7AL, UK

I am an Assistant Professor of ML/AI at the Department of Computer Science of the University of Warwick. Before that, I was a Research Faculty member at the Mathematical Institute for Data Science (MINDS) of Johns Hopkins University (JHU), working with Professor Rene Vidal. From 2019 to 2022, I held a Marie-Sklodowska Curie postdoctoral fellowship at MINDS at JHU. My research area is a combination of machine learning and signal processing, with a focus on parsimonious representation learning and its applications in deep generative models and continual learning. My work is interdisciplinary and encompasses topics such as convex/nonconvex optimization theory, Bayesian inference, high-dimensional probability theory with applications in image processing/computer vision, and trustworthy ML.

news

Oct 10, 2024 I am excited to be serving as an Area Chair for both ICLR 2025 and AAMAS 2025!
Dec 10, 2023 I have joined the Department of the University of Warwick as an Assistant Professor of ML/AI! Currently, I am seeking a talented student to collaborate with for a fully funded PhD position. Please feel free to contact me if you are interested!
May 30, 2023 I am delighted to be serving as an Area Chair for the upcoming Conference on Parsimony and Learning, scheduled to be held at Hong Kong University (HKU) in January 2024! It is an honor to collaborate with exceptional colleagues and distinguished experts in this field.
May 28, 2023 Excited to give an invited talk at SIAM-OPT in Seattle (Thursday, June 1st) on Alternating Iteratively Reweighted Algorithms for Matrix and Tensor Decompositions!
May 4, 2023 New paper on theory of continual learning accepted to ICML 2023. Check it out here!

selected publications

  1. ICML
    The ideal continual learner: An agent that never forgets
    Liangzu Peng, Paris Giampouras, and René Vidal
    2023
  2. ICLR
    Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension
    Paris Giampouras, Benjamin Haeffele, and Rene Vidal
    International Conference on Learning Representations 2022
  3. IEEE TSP
    Block-Term Tensor Decomposition Model Selection and Computation: The Bayesian Way
    Paris Giampouras, Athanasios A. Rontogiannis, and Eleftherios Kofidis
    IEEE Transactions on Signal Processing 2022
  4. ICML
    Reverse Engineering \ell_p attacks: A block-sparse optimization approach with recovery guarantees
    Darshan Thaker *, Paris Giampouras *, and Rene Vidal
    (* equal contribution) 39th International Conference on Machine Learning 2022