Iman's Website

Iman Nodozi

Email: inodozi[at]ucsc[dot]edu

Hello! I am Iman, a Ph.D. candidate in the Department of Electrical and Computer Engineering at UC Santa Cruz. My research interests are Stochastic Control, Hybrid Systems, and Convex Optimization. I am working under the supervision of Abhishek Halder.

I enjoy hiking, watching movies, playing piano, surfing, and running in my free time.

Home	Research	Publications	Education	Experience	Awards	Vitae

News

2024

07/11:	Our work A Physics-informed Deep Learning Approach for Minimum Effort Stochastic Control of Colloidal Self-Assembly received the 2024 O. Hugo Schuck Best Application Paper Award from the American Automatic Control Council
05/15:	Our invited paper Solution of the Probabilistic Lambert's Problem: Optimal Transport Approach is accepted in 2024 Mathematical Theory of Networks and Systems
03/15:	I successfully passed my PhD defense: Measure-valued Proximal Recursions for Learning and Control
01/15:	New manuscript: Solution of the Probabilistic Lambert Problem: Connections with Optimal Mass Transport, Schrödinger Bridge and Reaction-Diffusion PDEs

2023

12/12:	Our paper Proximal Mean Field Learning in Shallow Neural Networks is accepted in Transactions on Machine Learning Research
11/23:	Our papers Neural Schrödinger Bridge with Sinkhorn Losses: Application to Data-driven Minimum Effort Control of Colloidal Self-assembly is accepted in IEEE Transactions on Control Systems Technology
09/13:	New manuscript: Wasserstein Consensus ADMM
07/26:	New manuscript: Neural Schrödinger Bridge with Sinkhorn Losses: Application to Data-driven Minimum Effort Control of Colloidal Self-assembly
07/11:	Our papers Optimal Mass Transport over the Euler Equation and A Controlled Mean Field Model for Chiplet Population Dynamics are accepted in 2023 CDC.
05/31:	I presented our work on " A Physics-informed Deep Learning Approach for Minimum Effort Stochastic Control of Colloidal Self-Assembly" in ACC 2023 , paper here
05/05:	I won the 2023-24 Baskin School of Engineering Dissertation Year Fellowship! .
04/07:	I co-chaired the 5th NorCal Control Workshop and presented our work: "Wasserstein consensus ADMM" . My colleague Alexis Teter also gave a talk on our work "Solution of the Probabilistic Lambert Problem" .
03/31:	New manuscript: Optimal Mass Transport over the Euler Equation
03/17:	New manuscript: A Controlled Mean Field Model for Chiplet Population Dynamics
01/19:	Our paper A Physics-informed Deep Learning Approach for Minimum Effort Stochastic Control of Colloidal Self-Assembly is accepted in 2023 ACC

2022

10/25:	New manuscript: Proximal Mean Field Learning in Shallow Neural Networks
09/15:	Prof. Abhishek Halder presented our work A Distributed Algorithm for Measure-valued Optimization with Additive Objective in the Invited Session "Optimal Transport in Networks and Systems" at MTNS 2022
09/12:	I started an internship at Onsemi as an applications engineer for Fall 2022.
08/21:	New manuscript: A Physics-informed Deep Learning Approach for Minimum Effort Stochastic Control of Colloidal Self-Assembly
07/15:	Our papers Schrödinger Meets Kuramoto via Feynman-Kac: Minimum Effort Distribution Steering for Noisy Nonuniform Kuramoto Oscillators and A Mixed Integer Approach for the Solution of Hybrid Model Predictive Control Problems are accepted in 2022 CDC
06/06:	Our invited paper A Distributed Algorithm for Measure-valued Optimization with Additive Objective is accepted in 2022 Mathematical Theory of Networks and Systems
06/03:	Delivered the talk Neural Schrödinger Bridge for Minimum Effort Self-assembly in the 4th NorCal control workshop
03/31:	New manuscript: A Mixed Integer Approach for the Solution of Hybrid Model Predictive Control Problems
02/18:	New manuscript: Schrödinger Meets Kuramoto via Feynman-Kac: Minimum Effort Distribution Steering for Noisy Nonuniform Kuramoto Oscillators
02/17:	New manuscript: A Distributed Algorithm for Measure-valued Optimization with Additive Objective
02/09:	I passed the Ph.D. Qualifying Exam: Measure-valued Proximal Recursions for Learning and Control