Nick Stergioulas is known for his contributions to the study of the equilibrium and stability of rotating relativistic stars, of relativistic accretion disks and of strongly-magnetized neutron stars (magnetars). He received his Ph.D. from the University of Wisconsin-Milwaukee, under the supervision of John L. Friedman, in 1996. He was a post-doctoral researcher at the Albert-Einstein-Institute, Potsdam (MPA for Gravitational Physics, 1998-1999) before joining the Department of Physics at the Aristotle University of Thessaloniki as a faculty member. He has more than 210 publications, out of which more than 120 refereed publications. His research topics include: Gravitational-wave astronomy; Compact stars as sources of gravitational waves; Equilibrium and instabilities of rotating relativistic stars; Nonlinear oscillations of relativistic stars; MHD oscillations in relativistic models of magnetized neutron stars; Numerical relativity; Interaction of gravitational waves with plasma; and Relativistic accretion disks. His publications have received a total of more than 10,100 citations with an h-index of 52.

Abstract:

Gravitational Wave Discoveries Enabled by Machine Learning

Gravitational wave astronomy has emerged as a new branch of observational astronomy, since the first detection of gravitational waves in 2015. The current number of 𝑂(100) detections is expected to grow by several orders of magnitude over the next two decades. As a result, current computationally expensive detection algorithms will become impractical. A solution to this problem, which has been explored in the last years, is the application of machine-learning techniques to accelerate the detection of gravitational wave sources. In particular, the AresGW algorithm, implemented using a 54-layer deep residual network has demonstrated remarkable ability in achieving a high detection rate in real noise. The results of the first Machine Learning Gravitation Wave Mock Data Challenge (MLGWSC-1) have underscored the effectiveness of the AresGW algorithm, highlighting its higher sensitivity over traditional detection algorithms, such as matched filtering or wavelet-based approaches. The introduction of Deep Adaptive Input Normalization (DAIN) and curriculum learning strategies have allowed substantial improvements in the training efficiency and robustness of AresW. This progress is poised to bring about a new era in gravitation-wave astronomy, where machine learning will pave new paths for exploration and discovery.