The 10th David Finney Lecture (2026) We are pleased to announce that the 10th David Finney Lecture will be presented by Prof Carey Priebe (Johns Hopkins University). Full details to be announced. You can read more about David Finney as well as watch some of the previous lectures here. Talk Details Title: Performance Guarantees for LLMs Abstract: Performance guarantees for LLMs are essential to myriad critical applications, enabling for any application for which quantifiable confidence in LLM performance is nonnegotiable, such as security, justice, medicine, etc. We develop theory and methods for providing performance guarantees for LLMs in the context of a map between vector embeddings. The Data Kernel Perspective Space (DKPS) provides a framework to generate empirically validated theoretical predictions allowing guaranteed performance quantification for these transformative models. I will present probability, statistics, and linear algebra for DKPS, and illustrative examples. About the Speaker Prof Carey E. Priebe Carey E. Priebe is Professor in the Department of Applied Mathematics & Statistics and Director of the Mathematical Institute for Data Science (MINDS) at Johns Hopkins University. He is an Elected Member of the International Statistical Institute, Senior Member of the IEEE, Fellow of the Institute of Mathematical Statistics, and Fellow of the American Statistical Association. His current work on foundations of AI is funded by DARPA, ONR, AFOSR, Microsoft, Amazon. Prof Priebe's Personal Webpage Dec 07 2026 1:30pm - 3:30pm The 10th David Finney Lecture (2026) The 10th David Finney Lecture will be presented by Prof Carey Priebe (Johns Hopkins University) in December 2026. TBC This article was published on Monday 19 October 2026
The 10th David Finney Lecture (2026) We are pleased to announce that the 10th David Finney Lecture will be presented by Prof Carey Priebe (Johns Hopkins University). Full details to be announced. You can read more about David Finney as well as watch some of the previous lectures here. Talk Details Title: Performance Guarantees for LLMs Abstract: Performance guarantees for LLMs are essential to myriad critical applications, enabling for any application for which quantifiable confidence in LLM performance is nonnegotiable, such as security, justice, medicine, etc. We develop theory and methods for providing performance guarantees for LLMs in the context of a map between vector embeddings. The Data Kernel Perspective Space (DKPS) provides a framework to generate empirically validated theoretical predictions allowing guaranteed performance quantification for these transformative models. I will present probability, statistics, and linear algebra for DKPS, and illustrative examples. About the Speaker Prof Carey E. Priebe Carey E. Priebe is Professor in the Department of Applied Mathematics & Statistics and Director of the Mathematical Institute for Data Science (MINDS) at Johns Hopkins University. He is an Elected Member of the International Statistical Institute, Senior Member of the IEEE, Fellow of the Institute of Mathematical Statistics, and Fellow of the American Statistical Association. His current work on foundations of AI is funded by DARPA, ONR, AFOSR, Microsoft, Amazon. Prof Priebe's Personal Webpage Dec 07 2026 1:30pm - 3:30pm The 10th David Finney Lecture (2026) The 10th David Finney Lecture will be presented by Prof Carey Priebe (Johns Hopkins University) in December 2026. TBC This article was published on Monday 19 October 2026
Dec 07 2026 1:30pm - 3:30pm The 10th David Finney Lecture (2026) The 10th David Finney Lecture will be presented by Prof Carey Priebe (Johns Hopkins University) in December 2026.
