Uploaded October 2026 | Updated November 2026, 3 days ago
Jeremias Sulam (Johns Hopkins University)
https://simons.berkeley.edu/talks/jeremias-sulam-johns-hopkins-university-2026-10-06
Trustworthy AI: From Hallucinations to Reliable Autonomy
Modern machine learning models are increasingly deployed in dynamic environments where reliability must be established continuously rather than assumed. In this talk, I will present two recent advances in sequential statistical inference that address complementary aspects of this challenge. I will first introduce efficient sequential hypothesis tests for continuously auditing deployed machine learning systems, enabling rapid detection of performance degradation while maintaining rigorous Type I error guarantees. I will then show how similar sequential perspectives lead to parameter-free online conformal prediction methods that provide adaptive, group-conditional uncertainty quantification under evolving data distributions. Together, these results illustrate how sequential inference provides a principled statistical framework for moving from detecting when models fail to quantifying when individual predictions can be trusted.
Jeremias Sulam (Johns Hopkins University)
https://simons.berkeley.edu/talks/jeremias-sulam-johns-hopkins-university-2026-10-06
Trustworthy AI: From Hallucinations to Reliable Autonomy
Modern machine learning models are increasingly deployed in dynamic environments where reliability must be established continuously rather than assumed. In this talk, I will present two recent advances in sequential statistical inference that address complementary aspects of this challenge. I will first introduce efficient sequential hypothesis tests for continuously auditing deployed machine learning systems, enabling rapid detection of performance degradation while maintaining rigorous Type I error guarantees. I will then show how similar sequential perspectives lead to parameter-free online conformal prediction methods that provide adaptive, group-conditional uncertainty quantification under evolving data distributions. Together, these results illustrate how sequential inference provides a principled statistical framework for moving from detecting when models fail to quantifying when individual predictions can be trusted.





![Ground Energy estimation of Quantum Impurity model is in BQP
Jiaqing Jiang (UC Berkeley)
https://simons.berkeley.edu/talks/jiaqing-jiang-uc-berkeley-2026-07-24
Quantum Summer Cluster Final Workshop
Estimating the ground-state energy of quantum many-body systems is a leading application of quantum computing. For general Hamiltonians, however, the problem is QMA-complete and is therefore unlikely to admit an efficient quantum algorithm. This motivates the search for natural classes of Hamiltonians whose ground-energy problem lies in BQP but is not known to lie in BPP.
In this talk, we identify quantum impurity Hamiltonians as one such class. These Hamiltonians are central to dynamical mean-field theory (DMFT), widely regarded as a gold-standard framework for studying strongly interacting quantum systems. Specifically, by explicitly constructing a guiding state, we give a polynomial-time quantum algorithm that estimates the ground-state energy of quantum impurity Hamiltonians to any inverse polynomial precision. Previously, the best unconditional upper bounds were a quasi-polynomial-time classical algorithm and containment of the corresponding decision problem in QCMA [Bravyi&Gosset arxiv:1609.00735]. Ground Energy estimation of Quantum Impurity model is in BQP](https://i.ytimg.com/vi/krqOy27VIu0/mqdefault.jpg)




