In this talk, we discuss current state-of-the-art optimization methods widely used in inverse problems. We then survey recent related advances in addressing similar challenges in problems faced by the machine learning community and discuss their potential advantages for solving inverse problems.
Sergey I. Kabanikhin, Communication academician, Siberian Branch of Russian Academy of Sciences. Chairman of the Scientific Committee of the Institute of Computational Mathematics and mathematical Geophysics of the Siberian Branch of the Russian Academy of Sciences, member of the presidium of the Siberian Branch of the Russian Academy of Sciences, member of the presidium of the Department of Mathematical Sciences of the Russian Academy of Sciences, and chairman of the supercomputing Committee of the Siberian Branch of the Russian Academy of Sciences. His main research direction is numerical methods of ill posed problems in geophysics, including seismic, electrical, gravity and magnetic exploration; CT scan; Deal with physical measurement, data interpretation and other issues in the application.