جستجوی استاد راهنمای دانشگاهی

Bin Gaoمشاهده پروفایل

دانشیار

• Riemannian Optimization
• Tensor Computation
• Parallel/Distributed Computing
• +۵ مورد دیگر

Bin Gao is an Associate Professor at the Academy of Mathematics and Systems Science (AMSS), Chinese Academy of Sciences. He holds a Ph.D. in Applied Mathematics (2019, University of Chinese Academy of Sciences) and a B.Sc. in Mathematics (2014, Sichuan University). His postdoctoral experience includes positions at UCLouvain (2019-2021) and the University of Münster (2021-2022). Research Interests: Riemannian optimization, tensor computation, parallel/distributed algorithms for orthogonality constraints, machine learning applications. Key Contributions: Development of retraction-free methods on Stiefel manifolds, preconditioned Riemannian algorithms, and geometric frameworks for symplectic eigenvalue problems. Article Trends: Recent work focuses on overcoming the curse of dimensionality via manifold-based optimization, including distributed algorithms for Stiefel manifolds, graph-regularized tensor completion, and second-order methods for symplectic structures. Keywords span numerical analysis, quantum information, and machine learning. Scientific Awards: 2021 Zhong Jiaqing Mathematics Award 2018 Best Student Paper Award (CSIAM) 2018 CAS Special President Scholarship 2017 National Scholarship for Doctoral Students (China) 2016 Honor Student Award (International Workshop on Modern Optimization and Application) Advising & Collaborations: Collaborates with researchers from UCLouvain, University of Münster, and AMSS. Mentors students in Riemannian optimization and tensor computation. Leads the popman research group.

Dominik Stögerمشاهده پروفایل

استادیار

• Mathematical Foundations of Data Science
• Non-convex Optimization
• Machine Learning Theory
• +۴ مورد دیگر

Dominik Stöger is an Assistant Professor (tenure-track) in the Department of Mathematics at KU Eichstätt-Ingolstadt since 2021, affiliated with the Mathematical Institute for Data Science and Machine Learning (MIDS). His research bridges mathematical theory and data science applications. His educational background includes: B.Sc. in Mathematics, Technical University of Munich (2013) M.Sc. in Mathematics, Technical University of Munich (2015) Ph.D. in Mathematics, Technical University of Munich (2019) Stöger's research centers on mathematical foundations of data science, with emphasis on non-convex optimization in machine learning, theoretical analysis of overparameterized models, and low-rank matrix recovery. He combines optimization theory and high-dimensional probability to develop rigorous guarantees for modern algorithms, addressing critical challenges in deep learning theory. His recent publications (2020-2025) demonstrate consistent output in top venues including COLT, NeurIPS, and ICLR, with particular focus on implicit regularization phenomena and non-convex recovery guarantees. The 2025 pipeline shows active work extending theoretical boundaries in matrix sensing and neural network analysis. Stöger has received significant recognition: NeurIPS 2021 Spotlight Paper (top 3% of submissions) COLT 2025 paper presentation As a tenure-track faculty member, he maintains active collaborations across institutions (USC, TUM) and likely advises graduate students. His research program shows strong momentum with multiple concurrent projects advancing theoretical machine learning. He contributes to the research ecosystem through affiliation with MIDS, fostering interdisciplinary work in mathematical data science at KU Eichstätt-Ingolstadt.