[Theory] NOW: 4/15 Talks at TTIC: Andrew Ilyas, MIT
Mary Marre
mmarre at ttic.edu
Mon Apr 15 10:58:30 CDT 2024
*When:* Monday, April 15, 2024 at* 11:00** am** CT *
*Where: *Talk will be given *live, in-person* at
TTIC, 6045 S. Kenwood Avenue
5th Floor, Room 530
*Virtually*: *via *Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=35ec4ced-7081-4442-ac9c-b1520162c2d2>*
)
* *limited access: see info below*
*Who: * Andrew Ilyas, MIT
------------------------------
*Title*: Making Machine Learning Predictably Reliable
*Abstract*: Despite ML models' impressive performance, training and
deploying them is currently a somewhat messy endeavor. But does it have to
be? In this talk, I overview my work on making ML “predictably
reliable”---enabling developers to know when their models will work, when
they will fail, and why.
To begin, we use a case study of adversarial inputs to show that human
intuition can be a poor predictor of how ML models operate. Motivated by
this, we present a line of work that aims to develop a precise
understanding of the ML pipeline, combining statistical tools with
large-scale experiments to characterize the role of each individual design
choice: from how to collect data, to what dataset to train on, to what
learning algorithm to use.
*Bio*: Andrew Ilyas is a PhD student in Computer Science at MIT, where he
is advised by Aleksander Madry and Constantinos Daskalakis. His research
aims to improve the reliability and predictability of machine learning
systems. He was previously supported by an Open Philanthropy AI Fellowship.
* Host: *Avrim Blum <avrim at ttic.edu>
Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL 60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
On Mon, Apr 15, 2024 at 9:58 AM Mary Marre <mmarre at ttic.edu> wrote:
> *When:* Monday, April 15, 2024 at* 11:00** am** CT *
>
>
> *Where: *Talk will be given *live, in-person* at
>
> TTIC, 6045 S. Kenwood Avenue
>
> 5th Floor, Room 530
>
>
>
> *Virtually*: *via *Panopto (*livestream
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=35ec4ced-7081-4442-ac9c-b1520162c2d2>*
> )
>
> * *limited access: see info below*
>
>
>
> *Who: * Andrew Ilyas, MIT
> ------------------------------
> *Title*: Making Machine Learning Predictably Reliable
>
> *Abstract*: Despite ML models' impressive performance, training and
> deploying them is currently a somewhat messy endeavor. But does it have to
> be? In this talk, I overview my work on making ML “predictably
> reliable”---enabling developers to know when their models will work, when
> they will fail, and why.
>
> To begin, we use a case study of adversarial inputs to show that human
> intuition can be a poor predictor of how ML models operate. Motivated by
> this, we present a line of work that aims to develop a precise
> understanding of the ML pipeline, combining statistical tools with
> large-scale experiments to characterize the role of each individual design
> choice: from how to collect data, to what dataset to train on, to what
> learning algorithm to use.
>
> *Bio*: Andrew Ilyas is a PhD student in Computer Science at MIT, where he
> is advised by Aleksander Madry and Constantinos Daskalakis. His research
> aims to improve the reliability and predictability of machine learning
> systems. He was previously supported by an Open Philanthropy AI Fellowship.
>
> * Host: *Avrim Blum <avrim at ttic.edu>
>
> *Access to this livestream is limited to TTIC / UChicago (press panopto
> link and sign in to your UChicago account with CNetID).
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue, Rm 517*
> *Chicago, IL 60637*
> *773-834-1757*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Sun, Apr 14, 2024 at 4:38 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:* Monday, April 15, 2024 at* 11:00** am** CT *
>>
>>
>> *Where: *Talk will be given *live, in-person* at
>>
>> TTIC, 6045 S. Kenwood Avenue
>>
>> 5th Floor, Room 530
>>
>>
>>
>> *Virtually*: *via *Panopto (*livestream
>> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=35ec4ced-7081-4442-ac9c-b1520162c2d2>*
>> )
>>
>> * *limited access: see info below*
>>
>>
>>
>> *Who: * Andrew Ilyas, MIT
>> ------------------------------
>> *Title*: Making Machine Learning Predictably Reliable
>>
>> *Abstract*: Despite ML models' impressive performance, training and
>> deploying them is currently a somewhat messy endeavor. But does it have to
>> be? In this talk, I overview my work on making ML “predictably
>> reliable”---enabling developers to know when their models will work, when
>> they will fail, and why.
>>
>> To begin, we use a case study of adversarial inputs to show that human
>> intuition can be a poor predictor of how ML models operate. Motivated by
>> this, we present a line of work that aims to develop a precise
>> understanding of the ML pipeline, combining statistical tools with
>> large-scale experiments to characterize the role of each individual design
>> choice: from how to collect data, to what dataset to train on, to what
>> learning algorithm to use.
>>
>> *Bio*: Andrew Ilyas is a PhD student in Computer Science at MIT, where
>> he is advised by Aleksander Madry and Constantinos Daskalakis. His research
>> aims to improve the reliability and predictability of machine learning
>> systems. He was previously supported by an Open Philanthropy AI Fellowship.
>>
>> * Host: *Avrim Blum <avrim at ttic.edu>
>>
>> *Access to this livestream is limited to TTIC / UChicago (press panopto
>> link and sign in to your UChicago account with CNetID).
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue, Rm 517*
>> *Chicago, IL 60637*
>> *773-834-1757*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>>
>> On Fri, Apr 12, 2024 at 11:25 PM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *When:* Monday, April 15, 2024 at* 11:00** am** CT *
>>>
>>>
>>> *Where: *Talk will be given *live, in-person* at
>>>
>>> TTIC, 6045 S. Kenwood Avenue
>>>
>>> 5th Floor, Room 530
>>>
>>>
>>>
>>> *Who: * Andrew Ilyas, MIT
>>> ------------------------------
>>> *Title*: Making Machine Learning Predictably Reliable
>>>
>>> *Abstract*: Despite ML models' impressive performance, training and
>>> deploying them is currently a somewhat messy endeavor. But does it have to
>>> be? In this talk, I overview my work on making ML “predictably
>>> reliable”---enabling developers to know when their models will work, when
>>> they will fail, and why.
>>>
>>> To begin, we use a case study of adversarial inputs to show that human
>>> intuition can be a poor predictor of how ML models operate. Motivated by
>>> this, we present a line of work that aims to develop a precise
>>> understanding of the ML pipeline, combining statistical tools with
>>> large-scale experiments to characterize the role of each individual design
>>> choice: from how to collect data, to what dataset to train on, to what
>>> learning algorithm to use.
>>>
>>> *Bio*: Andrew Ilyas is a PhD student in Computer Science at MIT, where
>>> he is advised by Aleksander Madry and Constantinos Daskalakis. His research
>>> aims to improve the reliability and predictability of machine learning
>>> systems. He was previously supported by an Open Philanthropy AI Fellowship.
>>>
>>> * Host: *Avrim Blum <avrim at ttic.edu>
>>>
>>>
>>>
>>> Mary C. Marre
>>> Faculty Administrative Support
>>> *Toyota Technological Institute*
>>> *6045 S. Kenwood Avenue, Rm 517*
>>> *Chicago, IL 60637*
>>> *773-834-1757*
>>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20240415/f577fa6f/attachment-0001.html>
More information about the Theory
mailing list