Saber Jafarpour
Research Assistant Professor
Department of Electrical, Computer, and Energy Engineering
University of Colorado Boulder
Email:
saber.jafarpour@colorado.edu
|
I am a Research Assistant Professor at the University of
Colorado Boulder. Before that, I was a Postdoctoral Research Fellow in the Decision and Control
Laboratory at the Georgia Institute of Technology working with Sam
Coogan and a Postdoctoral Research Fellow with the
Center for Control, Dynamical Systems, and Computation at the
University of California, Santa Barbara, working with
Francesco Bullo. I did my PhD in the Department of Mathematics and Statistics at Queen's
University under supervison of Andrew
Lewis.
Links: Google Scholar, Scopus,
IEEE Xplore,
Orcid ID: 0000-0002-7614-2940,
|
|
News:
July 2023: Our paper
Forward Invariance in Neural Network Controlled Systems
is accepted for publications in IEEE Control Systems Letters!
July 2023: Our paper A contracting dynamical system
perspective toward interval markov decision processes is accepted
for presentation at 62th IEEE Conference on Decision and Control
in Marina Bay Sands, Singapore!
July 2023: Our paper Contraction-guided adaptive partitioning for reachability analysis of neural network controlled systems is accepted
for presentation at 62th IEEE Conference on Decision and Control
in Marina Bay Sands, Singapore!
Mar. 2023: Our paper Interval Reachability of Nonlinear Dynamical
Systems with Neural Network Controllers is accepted
at 5th Annual Learning for Dynamics
and Control Conference (L4DC)!
Oct. 2022: Our preprint Monotonicity and contraction on polyhedral cones is available on arXiv!
Aug. 2022: Our paper Comparative Analysis of Interval Reachability for
Robust Implicit and Feedforward Neural Networks is accepted
for presentation at 61th IEEE Conference on Decision and Control
in Cancun, Mexico!
Aug. 2022: Our paper Non-Euclidean Monotone Operator Theory with
Applications to Recurrent Neural Networks is accepted
for presentation at 61th IEEE Conference on Decision and Control
in Cancun, Mexico!
Jun. 2022: Our paper Robust Training and Verification of Implicit Neural
Networks: a non-Euclidean Contractive Approach is accepted
for poster presentation at the ICML workshop on Formal
Verification of Machine Learning (WFVML 2022) in Baltimore, Maryland!
Mar. 2022: Our work Robustness Certificates for Implicit Neural
Networks: A Mixed Monotone Contractive Approach is accepted
at 4th Learning for Dynamics
and Control Conference (Oral Presentation: Top 10 precent
of submitted papers)
Jan. 2022: Our work Resilience of Input Metering in Dynamic Flow
Networks is accepted for presentation at 2022 American Control Conference
(ACC) in Atlanta!
Sep. 2021: Our paper,
Robust Implicit Networks via Non-Euclidean Contractions is
accepted in NeurIPS 2021!.
July 2021: Our paper, Distributed
and Time-Varying Primal-Dual Dynamics via Contraction
Analysis, is accepted for publication in IEEE Transactions on
Automatic Control.
July 2021: Our paper,
From Contraction Theory to Fixed Point Algorithms on Riemannian and
non-Euclidean Spaces, is accepted for 60th IEEE Conference on Decision and Control!
Apr. 2021: We posted two manuscripts on arXiv:
Non-Euclidean Contraction Theory for Robust Nonlinear Stability and
Non-Euclidean Contraction Theory for Monotone and Positive Systems.
Apr. 2021: Our paper,
Flow and Elastic Networks on the n-Torus: Geometry, Analysis and
Computation, is accepted for publication in SIAM Review, Research Spotlight.
Mar. 2021: Our paper,
Singular Perturbation and Small-signal Stability for Inverter Networks, is accepted for publication in IEEE Transactions on Control of
Network Systems.
Mar. 2021: Our paper,
Weak and Semi-Contraction for Network Systems and Diffusively-Coupled
Oscillators, is accepted for publication in IEEE Transactions on Automatic Control.
|