Iman Nodozi
Email: inodozi[at]ucsc[dot]edu
Hello! I'm Iman Nodozi, a recent Ph.D. graduate in Electrical and Computer Engineering from UC Santa Cruz, where I worked under the supervision of Abhishek Halder. My research focuses on Stochastic Control, Hybrid Systems, and Convex Optimization. I am currently working as a Senior Systems Engineer at onsemi.
Outside of work, I enjoy hiking, watching movies, playing piano, surfing, and running.
Home | Research | Publications | Education | Experience | Awards | Vitae |
---|
I study Measure-valued Proximal Recursions for Learning and Control. The overarching goal of my research is to investigate convex optimization problems over the space of probability measures. Several problems in machine learning and statistics can be cast in this form. This includes sampling from an unnormalized prior, policy iteration in reinforcement learning, mean-field dynamics of classification, and Wasserstein Generative Adversarial Network (GAN) via variants of stochastic gradient descent. Several problems in control theory can also be cast in this form. Exemplars include prediction and nonlinear estimation of conditional joint state distributions, optimal distribution steering a.k.a. Schrödinger bridge, and its zero-noise limit: optimal mass transport.