BEGIN:VCALENDAR
VERSION:2.0
PRODID:-// - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://tilos.ai
X-WR-CALDESC:Events for 
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260520T110000
DTEND;TZID=America/Los_Angeles:20260520T120000
DTSTAMP:20260520T035505
CREATED:20260227T004426Z
LAST-MODIFIED:20260518T201234Z
UID:8112-1779274800-1779278400@tilos.ai
SUMMARY:TILOS-HDSI Seminar: Inference-Time Algorithms: A Theoretical Lens on Tractability and Error Propagation
DESCRIPTION:Andrej Risteski\, Carnegie Mellon University \nAbstract: Modern AI systems are increasingly built by placing trained models inside larger computational loops. Inference-time algorithms are a basic instance of this idea: they use one or more trained models at test time to incorporate new information\, exploit pretrained models as priors\, and trade computational effort for accuracy\, sample quality\, or control. Examples include generator-verifier search for reasoning\, diffusion models for solving inverse problems\, and reward-guided generation. Theoretically\, this revisits a classical question from optimization and theoretical computer science: what can be done with access to an oracle? Here\, however\, the oracles are new and non-standard: they model the capabilities of large pretrained models\, making them powerful\, but also imperfect because they are learned. This combination leads to new questions about algorithm design and error propagation. \nThis talk studies two central aspects of this paradigm: computational efficiency and error propagation. The first vignette considers generator-verifier systems\, and shows how stochastic backtracking can trade additional computation for accuracy\, giving a principled version of test-time scaling even with imperfect learned oracles. The second vignette studies diffusion steering: when can we efficiently bias a pretrained diffusion model toward higher-reward samples while staying close to the original model? We show that tractability depends strongly on both the reward structure and the alignment objective\, and that simple primitives—such as sampling from linear tilts—can be surprisingly useful for handling richer reward classes. \nBased on https://arxiv.org/abs/2510.03149\, https://arxiv.org/abs/2602.16570\, https://arxiv.org/abs/2605.11361. \n\nAndrej Risteski is an Associate Professor at the Machine Learning Department in Carnegie Mellon University. Prior to that\, he was a Norbert Wiener Research Fellow jointly in the Applied Math department and IDSS at MIT. Dr. Risteski received his PhD in the Computer Science Department at Princeton University under the advisement of Sanjeev Arora. \nDr. Risteski’s research interests lie in the intersection of machine learning\, statistics\, and theoretical computer science\, spanning topics like (probabilistic) generative models\, algorithmic tools for learning and inference\, representation and self-supervised learning\, out-of-distribution generalization and applications of neural approaches to natural language processing and scientific domains. The broad goal of his research is principled and mathematical understanding of statistical and algorithmic problems arising in modern machine learning paradigms. \nZoom: https://bit.ly/TILOS-Seminars
URL:https://tilos.ai/event/tilos-hdsi-seminar-inference-time-algorithms-a-theoretical-lens-on-tractability-and-error-propagation/
LOCATION:HDSI 123 and Virtual\, 3234 Matthews Ln\, La Jolla\, CA\, 92093\, United States
CATEGORIES:TILOS Seminar Series
ATTACH;FMTTYPE=image/png:https://tilos.ai/wp-content/uploads/2026/02/risteski-andrej-e1772152946152.png
END:VEVENT
END:VCALENDAR