Andrew and Erna Viterbi Early Career Chair and Professor of Electrical and Computer Engineering, Computer Science, and Industrial and Systems Engineering
Education
- 2014, Doctoral Degree, Electrical Engineering, Stanford University
- 2011, Master's Degree, Electrical Engineering, Stanford University
- 2009, Bachelor's Degree, Electrical Engineering, Sharif University Of Technology
Biography
Mahdi Soltanolkotabi is the director of the center on AI Foundations for the Sciences (AIF4S) at the University of Southern California. He is also an associate professor in the Departments of Electrical and Computer Engineering, Computer Science, and Industrial and Systems engineering where he holds an Andrew and Erna Viterbi Early Career Chair. Prior to joining USC, he completed his PhD in electrical engineering at Stanford in 2014. He was a postdoctoral researcher in the EECS department at UC Berkeley during the 2014-2015 academic year.
Research Summary
Soltanolkotabi's research focuses on developing the mathematical foundations of modern data science and artificial intelligence via characterizing the behavior and pitfalls of contemporary nonconvex learning and optimization algorithms with applications in AI reliability and trustworithiness, Multimodal Foundation models, AI for Healthcare and Science, Specific research areas of interest include:
• Mathematical foundations of data science
• High-dimensional probability and statistics
• Statistical Inference and Uncertainty Quanti cation
• AI Safety and Reliability
• Theoretical and mechanistic understanding of foundation models (LLMs, VLMs,
etc.)
• Foundations of deep learning and representation learning
• Iterative algorithms and non-convex optimization
• Theory of algorithms, applied probability, random matrix theory, empirical process
theory and chaining, geometric functional analysis.
• AI for healthcare and medicine with a particular focus on multi-modal foundation
models reliability and evaluations
• Artificial intelligence for the biomedical sciences including computational imaging,
MR/medical imaging, microscopy, and Cryo-electron tomography (cryo-ET)
• Optimization, signal processing and machine learning.
• Learning with limited labels and transfer learning
• Large-scale distributed training
• Federated and continual learning
• Sparse/low-rank recovery, compressive sensing, and phase retrieval.
• Coded computing, edge computing, low-precision computing, and large-scale data
analytics over cloud infrastructure
Awards
- 2024 Amazon GenAI Research Award
- 2023 National Institute of Health NIH Director's New Innovator Award
- 2021 Viterbi School of Engineering Viterbi school of engineering junior researcher award
- 2020 Amazon Faculty Research Award
- 2019 IEEE Information Theory Society best paper award
- 2018 David and Lucile Packard Foundation Packard Fellowship in Science and Engineering
- 2018 Alfred P. Sloan Foundation Sloan Fellowhip in Mathematics
- 2017 National Science Foundation NSF Career Award
- 2017 Air-force Office of Scientific Research Air-force Office of Scientific Research Young Investigator Award.
- 2016 Kavali Fellow and participant in the Frontiers of Science Symposium (hosted by National Academy of Sciences)
- 2016 Participant in the Frontiers of Engineering Symposium (hosted by National Academy of Engineering)
- 2015 Google Faculty Research Award
- 2010 Stanford BENCHMARK Graduate Fellowship in Science and Engineering
- 2009 Department and Institute rank 1/800, Sharif University of Technology
