[WTI-trainee] FW: 1/21 FDS Colloquium: Alexander Lew (Yale), "Automatic Integration and Differentiation of Probabilistic Programs"

Fri Jan 16 15:06:17 EST 2026

Sharing this talk from a Wu Tsai Investigator.

Best,

Giovanna

Giovanna Guerrero-Medina, PhD [A button for name playback in email signature] <https://www.name-coach.com/giovanna-guerrero-medina>

She/Her/Ella

Asst. Director for Professional Development & Community,

Wu Tsai Institute at Yale

giovanna.guerrero-medina at yale.edu<mailto:giovanna.guerrero-medina at yale.edu>

616.643.7666 (cell)

wti.yale.edu<https://wti.yale.edu/>

From: Yale Foundations of Data Science <message at message.yale.edu>
Date: Friday, January 16, 2026 at 2:55 PM
To: Guerrero-Medina, Giovanna <giovanna.guerrero-medina at yale.edu>
Subject: 1/21 FDS Colloquium: Alexander Lew (Yale), "Automatic Integration and Differentiation of Probabilistic Programs"

To view this email as a web page, go here.<https://view.message.yale.edu/?qs=dcca492f466dbf1366dc3f5437f358f76bf5216312e15aa753eb620ccd73caaebeace7729a9e48f3621bb11f375ac41461f4c565350b97862d659481f4f440b99c4e2bee19f1d4f20e0cb02e5e2c4871>
[Placeholder]<https://click.message.yale.edu/?qs=ba745356450a2331b04bf94893ded1d3379f0cda091c8106edfbc08f5e8d83e5c0472e8c5bc99082a68f09aacf71b583e1e26c2760419f74>
FDS Colloquium Series
Automatic Integration and Differentiation of Probabilistic Programs
[https://fds.yale.edu/wp-content/uploads/2026/01/Screenshot-2026-01-05-at-3.12.03-PM-242x300.png]

Speaker: Alexander Lew

Assistant Professor of Computer Science

Yale University

Wednesday, January 21, 2026

11:30AM - 1:00PM

Lunch at 11:30am in 1307
Talk 12:00-1:00pm in 1327

Location: Yale Institute for Foundations of Data Science & Webcast, 219 Prospect Street, New Haven, CT 06511<https://click.message.yale.edu/?qs=ba745356450a2331426049fa29a2fbb46b2d1794f94c78526a013bb3f7075dc3d8d583ead12970216c7eae43e6dcd0d42f099c84f4224cfa> and via Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4cc83590-ff44-4425-b166-b3ca013d9fae<https://click.message.yale.edu/?qs=ba745356450a23319405546f8eaa1e8ccac95a47dd5c84eadfa35e9c7e2f6e357edb0f61b7679009db034f47d79bf694c0eabfda530ebff5>

________________________________

Abstract: By automating the error-prone math behind deep learning, systems such as TensorFlow and PyTorch have supercharged machine learning research, empowering hundreds of thousands of practitioners to rapidly explore the design space of neural network architectures and training algorithms. This talk will show how new programming language techniques—particularly generalizations of automatic differentiation—make it possible to generalize and extend such systems to support probabilistic models. Our tools can automate the computation of expected values, probability densities, and their gradients, as well as help users derive fast, low-variance, unbiased estimators of these quantities when they are too expensive to compute exactly, enabling orders-of-magnitude speedups in downstream optimization and inference problems. To illustrate the value of these techniques, I’ll show how they have helped us build systems for (1) auditable reasoning and learning in relational domains, enabling the detection of thousands of errors across millions of Medicare records, and (2) probabilistic inference over large language models, enabling small open models to outperform frontier models on several constrained generation benchmarks.

Speaker Bio: Alex’s research aims to automate and scale up principled probabilistic reasoning, drawing on techniques from programming languages, machine learning, Bayesian statistics, and cognitive science. Alex is especially interested in the theory and practice of probabilistic and differentiable programming languages.

Alex is also a member of the GenLM consortium<https://click.message.yale.edu/?qs=ba745356450a2331c2fcf95e5b701c34001f00208e77422bcd041faf239e18ff1b57f499a0025bde826dac3d85d0445b39a4dc8b23540972>, a multi-university partnership aiming to better control, compose, and understand language models using the probabilistic programming and Bayesian inference toolkits.

Add To: Google Calendar<https://click.message.yale.edu/?qs=ba745356450a233112c9f593bf6bf5fab4c82eeec37a262cc9a283290492153386f2be53607ef9cee817151b7b239383924ac762ccd5f350> | Outlook | iCal File<https://click.message.yale.edu/?qs=ba745356450a23314853eae714a54a199ac8599a9eba98cddb31591bacd8e088eba0a429721739a759c64f58e5784befaad6eab60dc6bbbc>

Upcoming Events

Jan 21
FDS Colloquium: Alexander Lew (Yale), “Automatic Integration and Differentiation of Probabilistic Programs”<https://click.message.yale.edu/?qs=ba745356450a23314856047a6ef82a535855668e81e82bb97516abe2da9becc336381b7bef9d0e7b7b5c17b9f06dc6ba2d99da97b9af92eb>

Jan 26
S&DS Seminar: Alan Edelman (MIT)<https://click.message.yale.edu/?qs=ba745356450a2331ec169f891b8114772ab94103e2229a97f1c85bed849b483f6a57186226c0a8f889aeaf184ad37a1f4a23ebc73c4e616a>

Jan 28
FDS Colloquium: Harsh Parikh (Yale), “Causal Inference Beyond Common Support”<https://click.message.yale.edu/?qs=ba745356450a2331c5e73588ae6d5b8cef2dd1a841d48a6de2fd041e1510b857940c6fa65a5a57161c9f04c1f023b9b64fccc0b44d039114>

Feb 02
S&DS Seminar: Cong Ma (University of Chicago)<https://click.message.yale.edu/?qs=ba745356450a2331acae601d6f09b17624bb1b1ebaecf319347f9e85bb0bd456e32f14083b63ea93e4cc2cbcc59c6759799ee9f632441a09>

Feb 04
FDS Colloquium: Brian Burke (ESPN), “A Solution to the Performer-Context Paradox”<https://click.message.yale.edu/?qs=ba745356450a23315d1dab6d10c957726e37e7d8ead9ffc461b7196f110ae2d9d2ad85efd91c2d926459150ccb742bf8033f4a128b5b3490>

Feb 05
FDS Colloquium: Yuhai Tu (Flatiron), “Physics for Deep Learning: Towards a Theoretical Foundation”<https://click.message.yale.edu/?qs=ba745356450a2331fb2def00f8121905c16f5a8a7c74aa8f3121f09ef6663799f30695273d006df9a6849652a7ae7d4f99e9ab724d0ee51d>

Feb 06
S&DS Seminar: Joel A. Tropp (Caltech)<https://click.message.yale.edu/?qs=ba745356450a2331c60a7e6e3d6e8e206153b657177ba175fc0a8bfafab07b5793bc006dcb725c520f3cbb7c5c3a46a73fac919bc73cc255>

Feb 11
FDS Colloquium: Jaime Tucker-Foltz (Yale)<https://click.message.yale.edu/?qs=ba745356450a2331b6bb3919beaa7d333865f0e6de1cbdabc8624832bce6b67d3b110c45e75288276a4ae6c76356fee9d911ff0b3a2e9eed>

Feb 18
FDS Colloquium: David Holtz (Columbia)<https://click.message.yale.edu/?qs=ba745356450a2331ea6dedcdf7793190bd216b2bdefd811fa9d6edc65fdf12185321c0da1dfa385ac75d87ce370edeb69c4394d90a112eaa>

Feb 25
FDS Colloquium: Dean Eckles (MIT)<https://click.message.yale.edu/?qs=ba745356450a2331de86244cdcabecc2d87ba849c421c80b97d025c15d346d2a09cd42a83931965d898b52ed055985222bf4e6287c0f8fc5>

Contact

Emily E. H. Hau | Associate Director
Yale Institute for Foundations of Data Science (FDS), Yale University
emily.hau at yale.edu<mailto:emily.hau at yale.edu?subject=>
P: 203-436-4732

US Mail: Kline Tower, P.O. Box 208328, New Haven CT 06520-8328
Courier: Kline Tower, 219 Prospect Street, Room 1333, New Haven, CT 06511

[https://image.message.yale.edu/lib/fe4615707564057d761672/m/1/a6b6f1f4-d951-4540-b993-6d3607eddeeb.jpg]<https://click.message.yale.edu/?qs=ba745356450a2331c71cb406a8040387a140d4657f05b885edf9bc4c3c3cb6eb27acffdde3007642bfff2765f6ba9c2a651159b1aa7a389a>
This email was sent by: Yale University
P.O. Box 208327, New Haven, CT, 06520-8327 USA

Update Your Preferences<https://click.message.yale.edu/?qs=ba745356450a23317ebce567625bad4cd20f8f6b4c2b7fc11d43d5e4acdac66664088c3b49c521a8ac3d361d8b4f9fdc15072025a8234ada>      Privacy Policy<https://click.message.yale.edu/?qs=ba745356450a2331ea34ae9ebafc912f0b1a828cd715e48f6e6bd69c99d9acfec21704be1bc97fd19aef58674e6b8e8bc2d88058225d93ac>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/wti-trainee/attachments/20260116/ed77afd5/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001[7].png
Type: image/png
Size: 2131 bytes
Desc: image001[7].png
URL: <http://mailman.yale.edu/pipermail/wti-trainee/attachments/20260116/ed77afd5/attachment-0001.png>