Me, Prasanna Balaprakash (https://www.linkedin.com/in/prasannaprakash/) and Jayaraman J. Thiagarajan (https://www.linkedin.com/in/jjayaram7/) are organizing a minisymposium on “Robust and Efficient Probabilistic Deep Learning for Scientific Data and Beyond” at the SIAM Conference on Uncertainty Quantification (https://lnkd.in/eVQ-hVK5 ), that is taking place from April 12-15. We will be highlighting the latest advances in probabilistic deep learning, both from the Bayesian and frequentist perspective with focus on efficiency and robustness.
We will be looking forward for your attendance. The recorded sessions will also be available for registered participants
Our awesome speaker lineup is as follows: 1. Andrew Wilson (https://lnkd.in/e_PCBaKy) talking about “How Do We Build Models That Learn and Generalize?” 2. Shrijita Bhattacharya talking on “Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details” 3. Ian Fischer (https://lnkd.in/egCNRUyn) talking on “Information Theoretic Objectives, Generalization, and Robustness” 4. Bo Li (https://lnkd.in/e6Z2-Zyt) talking on “Trustworthy Machine Learning via Logic Inference” 5. Shubhendu Trivedi talking on “Locally Valid and Discriminative Prediction Intervals for Deep Learning Models” 6. I`m giving a talk on “Information-Preserving Bayesian Models for Efficient and Robust Learning” 7. Rushil Anirudh talking on “Delta-UQ: Accurate Uncertainty Quantification via Anchor Marginalization” 8. Salman Habib giving a talk on “Machine Learning, Systematics, and Statistics: A Cosmological Perspective” 9. Mohamed Aziz Bhouri (https://lnkd.in/enqfTNPV) taking on “Gaussian Processes Meet Neural ODEs: A Bayesian Framework for Learning the Dynamics of Partially Observed Systems from Scarce and Noisy Data” 10. Prasanna Balaprakash giving a talk on “Autodeuq: Automated Deep Ensemble with Uncertainty Quantification”