Research interests lie at the intersection of large-scale continuous optimization, inverse problems in imaging, generative learning, and image classification.
Current research focuses on optimization and generative learning with applications to image processing and computer vision.
Key methodological interests include Majoration-Minimization, proximal algorithms, subspace acceleration, and convergence theory.
Works on image restoration and reconstruction within the Bayesian framework, and generative models such as flow-based models, GANs, and VAEs.
Explores clustering and few-shot optimization-based methods, unbalanced few-shot learning, transductive learning, and text-vision models.