The 1W-MINDS Seminar was founded in the early days of the COVID-19 pandemic to mitigate the impossibility of travel. We have chosen to continue the seminar since to help form the basis of an inclusive community interested in mathematical data science, computational harmonic analysis, and related applications by providing free access to high quality talks without the need to travel. In the spirit of environmental and social sustainability, we welcome you to participate in both the seminar, and our slack channel community! Zoom talks are held on Thursdays at 2:30 pm New York time. To find and join the 1W-MINDS slack channel, please click here.
Current Organizers (September 2025 - May 2026): Ben Adcock (Simon Fraser University), March Boedihardjo (Michigan State University), Hung-Hsu Chou (University of Pittsburgh), Diane Guignard (University of Ottawa), Longxiu Huang (Michigan State University), Mark Iwen (Principal Organizer, Michigan State University), Siting Liu (UC Riverside), Kevin Miller (Brigham Young University), and Christian Parkinson (Michigan State University).
Most previous talks are on the seminar YouTube channel. You can catch up there, or even subscribe if you like.
To sign up to receive email announcements about upcoming talks, click here.
To join MINDS slack channel, click here.
Passcode: the smallest prime > 100
In this talk I will discuss a general framework for unifying multiple problems in scientific machine learning (ML), in particular equation learning, PDE solvers, and operator learning. I will discuss how equation learning sits at the center of scientific ML and how it relates to classic ideas in control, inverse problems, and data assimilation.
Then I will present an efficient kernel method that can learn equations and their solution maps implicitly. I will present some interesting numerical benchmarks as well as theoretical support in the form of convergence rates.
Training safe and helpful language models requires aligning them with human preferences. In this talk, I will present a series of works that reveal fundamental pitfalls in the two most widely adopted alignment methods: Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO). First, I will show that RLHF suffers from a flat objective landscape when the reward model induces low reward variance. This issue can arise even if the reward model is highly accurate—challenging conventional wisdom that more accurate reward models are better teachers and highlighting limitations of existing reward model benchmarks. Then, we will focus on DPO and see that it can fail to reliably increase the likelihood of generating preferred outputs, sometimes even causing the model to generate outputs with an opposite meaning. In particular, aligning a model to refuse answering unsafe prompts can unintentionally unalign it by shifting probability mass from preferred safe outputs to harmful ones. Beyond characterizing these pitfalls, our theory provides quantitative measures for identifying when they occur, suggests preventative guidelines, and has led to the development of new data selection and alignment algorithms.
In this talk, we argue that "inference-time" Large Language Model (LLM) operation, where we interact with these models post-training without modifying their weights, is fertile ground for information-theoretic methods. We focus on one challenge in particular: watermarking LLM-generated text. Watermarks enable authentication of text provenance and help curb misuse of machine-generated content. We present recent results establishing a close connection between LLM watermarking and coding theory, showing that classical tools such as the Plotkin bound yield fundamental limits on watermark performance. This perspective also informs the design of two practical watermarks: SimplexWater and HeavyWater. We show that these watermarks achieve high detection accuracy with minimal impact on text quality, even in low-entropy tasks such as code generation. We also briefly survey other inference-time challenges that can be addressed with information theory, such as inference-time alignment. These results illustrate a broader opportunity: as LLMs increasingly serve as black-box components of more complex systems, information and coding theory offer a principled toolkit for shaping, verifying, and controlling their outputs.