Events
Statistics & Data Science Seminar
"Scaling Inference-Time Compute: From Self-Improvement to Pessimism"
 |
Speaker: Adam Block (Columbia) Department of Computer Science, Columbia University Columbia University Monday, October 20, 2025 3:30PM - 5:00PM Teatime at 3:30pm in 1307
Talk at 4:00pm in 1327 Location: Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511 and via Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=6d1b3346-6…(Link is external) |
Abstract: Language models increasingly rely on scaling inference-time computation to achieve state-of-the-art performance on a growing number of reasoning tasks. A popular paradigm for such computational scaling is Best-of-N (BoN) sampling, where a model generates multiple candidate responses to a given question and selects the one among them as the most likely to be correct. In this talk I will present a unified understanding of this approach in several settings, both with and without external verification. We will discuss the extent to which such inference-time computation is necessary as well as present a new algorithm that optimally leverages inference-time compute to return better answers in the presence of uncertainty, thereby avoiding common pitfalls of BoN sampling such as reward-hacking and over-optimization. Throughout, we will see that model coverage of ‘good’ answers emerges as the critical feature allowing for inference-time computation to scale effectively. These results provide a principled foundation for designing inference-time algorithms that scale reliably with compute and highlight coverage as the central bottleneck in aligning language models.
Add To: Google Calendar | Outlook | iCal File
- Statistics & Data Science Seminar
Submit an Event
Interested in creating your own event, or have an event to share? Please fill the form if you’d like to send us an event you’d like to have added to the calendar.