Minisymposium (ID: SS-AIO)

Artificial Intelligence, Inverse Problems, and Optimization

Herb Kunze (University of Guelph), Davide La Torre (SKEMA Business School, Universite Cote d'Azur), Oleg Michailovich (University of Waterloo) and Roman Smirnov (Dalhousie University)

This session highlights recent advances at the intersection of artificial intelligence, inverse problems, and optimization, emphasizing both theoretical developments and practical applications. Topics include learning-based and physics-informed approaches for inverse problems; data-driven and hybrid model–data methods; regularization techniques and their interpretation in modern learning frameworks; uncertainty quantification and robustness; and the integration of deep learning with classical variational, probabilistic, and Bayesian formulations. The session also covers optimization methods for large-scale and nonconvex problems arising in inverse modeling and machine learning, including stochastic, distributed, and accelerated algorithms. Applications of interest range from imaging and signal processing to scientific computing, engineering, economics, and the physical sciences.

---

Please note the ID code assigned to your presentation (identical to the ID code of your accepted abstract). It is required for submitting your paper for the AMMCS-2026 Proceedings. Submission is not mandatory. All submitted papers will be refereed and only accepted papers will be published in the AMMCS-2026 Proceedings.

If you intend to submit your paper, please go to the AMMCS Proceedings Page. Follow exactly the Author Instructions accessible from that page.