René Vidal, PhD

Center for Innovation in Data Engineering and Science (IDEAS)
Rachleff & Penn Integrates Knowledge (PIK) University Professor
Department of Electrical and Systems Engineering & Radiology
Department of Computer and Information Science
Department of Statistics and Data Science
University of Pennsylvania

3401 Walnut Street, Room 463C.
Philadelphia PA 19104, USA

Phone: 215-746-1726
E-mail: vidalr at upenn dot edu
About me
René Vidal is the Rachleff and Penn Integrates Knowledge (PIK) University Professor of Electrical and Systems Engineering & Radiology and the Director of the Center for Innovation in Data Engineering and Science (IDEAS) at the University of Pennsylvania. He is also the director of THEORINET, an NSF-Simons Collaboration on the Mathematical Foundations of Deep Learning, an Amazon Scholar and an Affiliated Chief Scientist at NORCE. His current research focuses on the foundations of deep learning and trustworthy AI and its applications in computer vision and biomedical data science. Dr. Vidal is an ACM Fellow, AIMBE Fellow, IEEE Fellow, IAPR Fellow and Sloan Fellow, and has received numerous awards for his work, including the IEEE Edward J. McCluskey Technical Achievement Award, D’Alembert Faculty Award, J.K. Aggarwal Prize, ONR Young Investigator Award, NSF CAREER Award as well as best paper awards in machine learning, computer vision, controls, and medical robotics.
Research Interests
  • Machine learning: mathematics of deep learning (non-convex optimization, learning dynamics, overparametrization), manifold learning and clustering (sparse subspace clustering, low-rank subspace clustering, generalzied principal component analysis), sparse and low-rank representation, matrix and tensor factorization, time series classification, GPCA, kernel GPCA, dynamic GPCA
  • Computer vision: visual grounding, scene interpretation, activity recognition, pose estimation, 3D scene analysis, semantic segmentation of images and videos, dynamic texture segmentation and recognition, 3D motion segmentation, camera sensor networks, non-rigid shape and motion analysis, structure from motion and multiple view geometry, omnidirectional vision
  • Biomedical data science: computer vision for pedriatic rehabilitation, computer vision for austism diagnosis, computer vision for Tourette symdrom diagnosis, gesture and skill recognition in robotic surgery, analysis of high angular resolution diffusion images (HARDI), classification of stem cell derived cardiac myocites, interactive medical image segmentation segmentation and fiber tracking in cardiac MRI, interactive medical image segmentation, heart motion analysis
  • Dynamical systems: observability, identification, realization, metrics and topology for hybrid systems
  • Robotics: gesture and skill recognition in robotic surgery, formation control of teams of non-holonomic robots, coordination and control of multiple autonomous vehicles for pursuit-evasion games, multiple view motion estimation and control for landing an unmanned aerial vehicle
  • Signal processing: consensus on manifolds, distributed optimization, compressive sensing.
  • Recent Talks
  • Dual Principal Component Pursuit, Invited Talk, Faraway Fourier Talks, March 2021.
  • Mathematics of Deep Learning, Plenary lecture, DeepMath, October 2020.
  • Mathematics of Deep Learning, Tutorial, The Analytical Foundations of Deep Learning: Interpretability and Performance Guarantees, 2020.
  • From Optimization Algorithms to Continuous Dynamical Systems and Back. Learning for Dynamics and Control (L4DC)p, MIT, May 31, 2019.
  • From Optimization Algorithms to Dynamical Systems and Back. Physics ∩ ML Workshop, Microsoft Research, April 25, 2019.
  • Computer Vision: History, the Rise of Deep Networks, and Future Vistas, Invited talk, Panel on Perception and Cognition, MORS Meeting on Artificial Intelligence and Autonomy, February 2019.
  • Mathematics of Deep Learning, Invited talk, Medical Imaging Summer School, Favignana, Italy, July-August 2018.
  • Mathematics of Deep Learning, Invited talk, 2nd International Summer School on Deep Learning, Genova, Italy, July 2018.
  • Artificial Intelligence and Machine Learning in Biomedicine and Health Care, Invited talk, AAMC Grand Spring Conference, Washington DC, 2018.
  • Global Optimality in Structured Matrix Factorization, Invited talk, ICCV Workshop on Robust Subspace Learning and Computer Vision, Santiago de Chile, 2015.
  • Algebraic, Sparse and Low Rank Subspace Clustering, Tutorial on Subspace Learning, CVPR June 2015
  • Globally Optimal Factorizations, Deep Learning and Beyond, KAUST March 2015, MACV April 2015, SSDS June 2015
  • Bio
    Professor Vidal received his B.S. degree in Electrical Engineering (valedictorian) from the Pontificia Universidad Catolica de Chile in 1997 and his M.S. and Ph.D. degrees in Electrical Engineering and Computer Sciences from the University of California at Berkeley in 2000 and 2003, respectively. He was a Research Fellow at the National ICT Australia from September to December of 2003, and an Assistant and Associate Professor in the Department of Biomedical Engineering of The Johns Hopkins University from 2004 to 2010 and from 2010 to 2015, respectively. Dr. Vidal is currently a Full Professor in the Department of Biomedical Engineering of Johns Hopkins University with secondary appointments in Computer Science, Electrical and Computer Engineering, Mechanical Engineering. He is also a faculty member in the Center for Imaging Science, the Institute for Computational Medicine and the Laboratory for Computational Sensing and Robotics. In 2017, he became the Innaugural Director of the Mathematical Institure for Data Science (MINDS). He has held several visiting faculty positions at ENS Paris-Saclay, Stanford, INRIA/ENS Paris, the Catholic University of Chile, Universite Henri Poincare, and the Australian National University. Dr. Vidal is co-author of the book ``Generalized Principal Component Analysis" (2016), co-editor of the book ``Dynamical Vision" and co-author of over 200 articles in machine learning, computer vision, biomedical image analysis, hybrid systems, robotics and signal processing. Dr. Vidal is or has been Associate Editor in Chief of Computer Vision and Image Understanding, Associate Editor of Medical Image Analysis, the IEEE Transactions on Pattern Analysis and Machine Intelligence, the SIAM Journal on Imaging Sciences, Computer Vision and Image Understanding, and the Journal of Mathematical Imaging and Vision, and guest editor of the International Journal on Computer Vision and Signal Processing Magazine. He is or has been program chair for ICCV 2015, CVPR 2014, WMVC 2009 and PSIVT 2007. He was area chair for AAAI 2016, NIPS 2015, MICCAI 2013 and 2014, ICCV 2007, 2011, 2013 and 2017, and CVPR 2005, 2013 and 2017. Dr. Vidal is recipient of numerous awards, including the 2017 Jean D'Alembert Faculty Fellowship, the 2012 J.K. Aggarwal Prize for ``outstanding contributions to generalized principal component analysis (GPCA) and subspace clustering in computer vision and pattern recognition", the 2012 Best Paper Award in Medical Robotics and Computer Assisted Interventions (with Benjamin Bejar and Luca Zappella), the 2011 Best Paper Award Finalist at the Conference on Decision and Control (with Roberto Tron and Bijan Afsari), the 2009 ONR Young Investigator Award, the 2009 Sloan Research Fellowship, the 2005 NFS CAREER Award and the 2004 Best Paper Award Honorable Mention (with Prof. Yi Ma) at the European Conference on Computer Vision. He also received the 2004 Sakrison Memorial Prize for "completing an exceptionally documented piece of research", the 2003 Eli Jury award for "outstanding achievement in the area of Systems, Communications, Control, or Signal Processing", the 2002 Student Continuation Award from NASA Ames, the 1998 Marcos Orrego Puelma Award from the Institute of Engineers of Chile, and the 1997 Award of the School of Engineering of the Pontificia Universidad Catolica de Chile to the best graduating student of the school. He is a fellow of the IEEE (2014), fellow of the IAPR (2016), and a member of the ACM and SIAM.

    Complete CV.

    Current Research Scientists and PostDocs
  • Benjamin Haeffele (Associate Research Scientist, 2015-present): optimization and generalization theory for deep learning, cell reconstruction, detection, classification and tracking
  • Paris Giampouras (Postdoctoral Researcher, 2019-present): matrix factorization, adversarial robustness
  • Stewart Slocum (Assistant Research Scientist, 2021-present): optimization theory for deep learning, semantic information pursuit
  • Current Graduate Students
  • Kyle Poe (2022-present, BME, JHU): learning and control
  • Steven Kan (2021-present, CS, JHU): adversarial robustness
  • Liangzu Peng (2021-present, ECE, JHU): geometric vision
  • Ziqing Xu (2021-present, AMS, JHU): learning dynamics of overparametrized models
  • Ryan Chan (2021-present, ECE, JHU): explainable AI, transformer architectures
  • Kaleab Kinfu (2021-present, CS, JHU): adversarial robustness, computer vision for autism diagnosis
  • Tianjiao Ding (2020-present, CS, JHU): subspace clustering
  • Yutao Tang (2020-present, BME, JHU): computer vision for tic detection
  • Darshan Thaker (2020-present, CS, JHU): adversarial robustness
  • Salma Tarmoun (2020-present, AMS, JHU): learning dynamics of overpaarmetrized models
  • Hancheng Min (2019-present, ECE, JHU, primary advisor Enrique Mallada)
  • Aditya Cattopadhyay (2018-present, CS, JHU): semantic information pursuit
  • Ambar Pal (2018-present, CS, JHU): adversarial robustness, implicit bias of dropout
  • Carolina Pacheco (2018-present, BME, JHU): cardiomyocyte classification, cell reconstruction, detection and counting
  • Alumni
  • Efi Mavroudi (PhD BME 2015-2022): action recognition
  • Florence Yellin (PhD ME 2015-2021): convolutional sparse coding and dictionary learning for cell classification
  • Guilherme Franca (postdoc, 2016-2012): a dynamical systems perspective to optimization algorithms in machine learning
  • Connor Lane (MSc CS, 2016-2019): math of deep learning
  • Zhihui Zhu (Postdoc, 2018-2019, now Assistant Professor at the University of Denver): non-convex optimization, subspace clustering, matrix factorization
  • Benjamin Bejar (Associate Research Scientist, 2017-2019, now Scientist at Swiss Data Science Center): blood cell tracking, action classification
  • Siddharth Mahendran (PhD ECE 2018, now research scientist at Magic Leap): 3D object modeling and semantic segmentation
  • Chong You (PhD ECE 2018, now postdoc at UC Berkeley): scalable and robust sparse subspace clustering
  • Haider Ali (Associate Research Scientist, 2017-2018): 3D scene analysis and activity recognition
  • Evan Schwab (PhD ECE 2017, now research scientist at Philips): analysis of diffusion MRI data
  • Giann Gorospe (PhD BME, 2017): classification of cardiac myocites, computational anatomy
  • Lingling Tao (PhD ECE 2016, now Research Scientist at Oculus VR): activity segmentation and classification
  • Manolis Tsakiris (PhD ECE 2016, now Tenured Associate Professor at Chinese Academy of Sciences): algebraic subspace clustering and sparse coding on the sphere
  • Colin Lea (PhD CS 2016, now Research Scientists at Oculus Research): fine-grained action recognition (coadvised with Greg Hager and Austin Reiter)
  • Shahin Sefati (postdoc 2015, now Senior Researcher at Comcast): dynamic sparse coding and dictionary learning
  • Benjamin Haeffele (PhD BME 2015, then Associate Research Scientist at JHU): structured matrix factorization and globally optimal deep learning
  • Bijan Afsari (postdoc 2010-2014, then Research Scientist 2014-2016): averaging on Riemannian manifolds, metrics on dynamical systems, activity recognition
  • Benjamin Bejar (MSc BME 2013, then postdoc at EPFL, then Associate Research Scientist at JHU): language of surgery
  • Erdem Yoruk (post-doc 2012-2013, now Chief Scientist at Vispera Information Technologies): modeling and inference for visual recognition
  • Luca Zappella (post-doc 2011-2013, then Senior Research Engineer at Metaio, now R&D Engineer at Apple): language or surgery, motion segmentation
  • Aastha Jain (post-doc 2012, now Senior Data Scientist at Linkedin): joint segmentation and categorization of objects in images and videos
  • Roberto Tron (PhD ECE 2012, then postdoc at Upenn, now Assistant Professor at Boston University): consensus on manifolds, localization of camera sensor networks, motion segmentation
  • Rizwan Chaudhry (PhD CS 2012, then Software Engineer at Microsoft and Nest-Google, now at Google Health): kernels on dynamical systems and activity recognition
  • Ehsan Elhamifar (PhD ECE, 2012, then postdoc at UC Berkeley, now Assistant Professor at Northeastern University): sparse subspace clustering, block-sparse classification, manifold clustering, robust consensus, observability and identification of hybrid systems
  • Ertan Cetingul (PhD BME 2011, then Research Scientist at Siemens Corporate Research, now Research Program Manager at GE): fiber tracking, heart motion analysis, processing, segmentation and registration of diffusion weighted images
  • Diego Rother (post-doc 2009-2011, now Software Engineer at Google): object segmentation, reconstruction and recognition using 3D shape priors
  • Avinash Ravichandran (PhD ECE 2010, then postdoc at UCLA, now Research Scientist at Amazon): registration, segmentation and recognition of dynamic textures
  • Dheeraj Singaraju (PhD ECE 2010, then postdoc at UC Berkeley, now Software Engineer at Google): discrete optimization, object recognition and segmentation, image matting and segmentation, 2D motion segmentation
  • Alvina Goh (PhD BME 2010, then Lab Head DSO National Laboratories Singapore, now Lead Computational Scientist at GovTech Singapore): estimation and processing of diffusion weighted images, manifold clustering
  • Mihaly Petreczky: (post-doc 2007-2008, then Assistant Professor at CWI Netherlands and Ecole des Mines de Douai, now Research Scientist at CNRS) realization theory for hybrid systems
  • Prospective Students
    If you are interested in joining my lab, please apply directly to the department your are most interested in: Applied Mathematics and Statistics (AMS), Biomedical Engineering (BME), Computer Science, (CS) Electrical and Computer Engineering (ECE), or Mechanical Engineering (ME). Please make sure to mention my name in your application and statement of purpose. Once you have applied, please send me an e-mail with a subject such as 'PhD Application to XXX YYYY', where XXX = AMS, BME, CS, ECE, ME is the department you have applied to, and YYY is the year you plamn to star your PhD. I will not respond emails, but I'll look at applicants that have sent me emails.