[WTI-trainee] FW: 10/22 FDS Colloquium: Mike Winer (IAS), “Heuristic Estimation of Neural Network Outputs”

[Guerrero-Medina, Giovanna]

Sharing in case it’s of interest.

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

Professional Development & Community,

Wu Tsai Institute at Yale

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





From: Yale Foundations of Data Science <message at message.yale.edu>
Date: Thursday, October 16, 2025 at 4:22 PM
To: Guerrero-Medina, Giovanna <giovanna.guerrero-medina at yale.edu>
Subject: 10/22 FDS Colloquium: Mike Winer (IAS), “Heuristic Estimation of Neural Network Outputs”


To view this email as a web page, go here.<https://view.message.yale.edu/?qs=af198917b30c49e5dd0648a3a295ce2c6ad0761f3ae9d16937eb0131017cb07345a37a9e206d448c5f8546a122d36b10a1cd6b201625c5dfea2839ccff1a5fb4d16b394ee2eeb470c8083c530550e34c>
[Placeholder]<https://click.message.yale.edu/?qs=03834ef9a7e3fe945a05333cd4d95072729999893a6570138271f4eeddc32a2fe1b544a5acb5b54347c99ea6a1d96600fdc60f34dacb41f6>
FDS Colloquium Series
"Heuristic Estimation of Neural Network Outputs"
[https://fds.yale.edu/wp-content/uploads/2025/09/Mike-Winer.jpg]

Speaker: Mike Winer

Marvin L. Goldberger Member, School of Natural Sciences, Institute for Advanced Study

Wednesday, October 22, 2025

11:30AM - 1:00PM

Lunch will be served at 11:30am in room 1307
Talk will be 12:00-1:00pm in 1327

Location: Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511<https://click.message.yale.edu/?qs=03834ef9a7e3fe94b7e98abe495dec1f44a0d79ab3297b115b629750e4bf81a0a590514865fc3f1b027095f4a5356875e920ef8efb50bde5> and via Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=fa8695d3-331c-40fa-9720-b35201057c71<https://click.message.yale.edu/?qs=03834ef9a7e3fe9437e63dc5060d3e8938d0b34be0fa5d14c81750ce7b5ab42312a851fa7d662f4168a4e4b6255331edcf6c18be6a21cced>

________________________________

Talk summary: Given a neural network and a description of its input distribution, what can we say about the outputs? In some sense we have all the information, but even estimating something like the frequency of a given rare token might require many forward passes. In this talk I discuss approximate techniques for answering these questions, often in manners much more computationally efficient than blindly producing forward passes. I discuss how these techniques shed light not only on what neural networks do on a given input, but why they do it.

Speaker bio: Michael Winer is a statistical physicist who studies disordered systems, their phase transitions, thermodynamics, and dynamics. Much of his work focuses on the physics of glasses and how it connects to broader questions in holography, deep learning, and the emergence of complex behavior from simple components. He is interested in how systems of many simple parts can organize into phenomena such as magnets, glasses, or intelligence. Michael currently divides his time between the Institute for Advanced Study in Princeton and the Alignment Research Center in Berkeley.

Add To: Google Calendar<https://click.message.yale.edu/?qs=03834ef9a7e3fe9491b0f6217afb1734686136dd69df07381e7fb60a4646f7a41a21fce53389dbbe69ff37ad5c8d7c64029e4447a778c850> | Outlook | iCal File<https://click.message.yale.edu/?qs=03834ef9a7e3fe94a363b87e963ca319166eb35ebf1ff8e26ca303b206b4a8bba0fb69e08c9a5cc6f286227c3759821eedc73c623b55975b>


Upcoming Events

Oct 16–17
FDS Workshop: New Directions in Social Algorithms Research<https://click.message.yale.edu/?qs=03834ef9a7e3fe944f0047b6e59afd5e56053f43a6e9278686b21fabb746201cfb8eead9c694352bd396292557817632d61fafdc920c10fb>
Registration Required.

Oct 20
S&DS Seminar: Adam Block (Columbia), “Scaling Inference-Time Compute: From Self-Improvement to Pessimism”<https://click.message.yale.edu/?qs=03834ef9a7e3fe94fd91c427cf53c42ad3af933172286d6606b45266299c6ad4fb890d8eedeae487b5d92e2d4381109c0fa02ef2926f4d62>

Oct 22
FDS Colloquium: Mike Winer (IAS), “Heuristic Estimation of Neural Network Outputs”<https://click.message.yale.edu/?qs=03834ef9a7e3fe94cc926c6b07da60495edcf7977b15bfcd7e2c394a2b80a47e41c886130857b81300c6552f2fec9fda01f7dd11f84035c2>

Oct 29
FDS Colloquium: Lorenzo Orecchia (Chicago)<https://click.message.yale.edu/?qs=03834ef9a7e3fe9450fe98541c90b9c896858f15407b76fb990a396069169c51ddbde4e5eaa3387f9001ca1b3845757bd4fde106a2152c3c>

Nov 12
FDS Colloquium: George Lan (Georgia Tech)<https://click.message.yale.edu/?qs=03834ef9a7e3fe94dd1c22f6351518eaaf026673d5ea44be1760f39d54d942365c1e7d19197136310d248f29448a4cafdc82b833664b473c>

Nov 19
FDS Postdoctoral Society, Johan Ugander (Yale), “Postdoc: What’s Next?”<https://click.message.yale.edu/?qs=03834ef9a7e3fe94202fce2d68c5b13fd88126f8311575a4d41f3b31c9805c4648d8b631aeb86ba350e9237e1fb64d4065b25114e830448b>
Postdocs and almost postdocs only.

Dec 10
FDS Colloquium: J. Nathan Kutz (UW), “Learning and Data Assimilation of Physics from Videos”<https://click.message.yale.edu/?qs=03834ef9a7e3fe94611e123e2b7d3edc282666f50f5695d6174ce93ccf032435ae3840dd6b2f475e0dae0958d875b740fe3e5076970f015b>


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=03834ef9a7e3fe94c6723ab734887672bbdda26c67bab9b301362f50bfb8e5eb442f5903f82336f6743eb5a29116066b20028cb4b83d828b>
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=03834ef9a7e3fe9479783b23325cab348bbb18f2b6a88875fca4fa79af4ee8d5803aa6dd7bf2f189a943f4e4e183b13e855955f6316d63a6>      Privacy Policy<https://click.message.yale.edu/?qs=03834ef9a7e3fe94081ef25148c97543a70967d2e9ef82c42996fd0e79ccb74ef157331dfe0756a57ac55b7fea8fb949736001a6cd023c16>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/wti-trainee/attachments/20251016/c34ad7bf/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 2131 bytes
Desc: image001.png
URL: <http://mailman.yale.edu/pipermail/wti-trainee/attachments/20251016/c34ad7bf/attachment-0001.png>