Ido Cohen, Omri Azencot, Pavel Lifshits, and Guy Gilboa. SIAM Journal on Imaging Sciences, 2021. Abstract Finding latent structures in data is drawing increasing attention in diverse fields such as image and signal processing, fluid dynamics, and machine learning. In this work, we examine the problem of finding the main modes of gradient flows. Gradient descent is a fundamental process in optimization where its stochastic version is prominent in the training of neural networks. Here our aim is to establish a consistent theory for gradient flows ψ(t)=P(ψ), where P is a nonlinear homogeneous operator. Our proposed framework stems from analytic…