[Theory] TODAY: 2/27 Talks at TTIC: Naomi Saphra, NYU

[Mary Marre]

*When:*        Monday, February 27, 2023 at* 11:30 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=8759978c-a0e0-4a2e-9f47-afaf0179b889>*
)



*Who: *        Naomi Saphra, NYU


------------------------------

*Title:*         Interpreting Training



*Abstract:* Interpretability research in NLP often follows a predictable
pattern—pick an indicator of structure or knowledge such as probe or
challenge set accuracy, measure that indicator in a fully trained model,
and assert that this structure or information is integral to how the model
functions. However, we can achieve a much deeper understanding by
considering how these indicators emerge from the training process. First,
this talk will discuss research on the relationship between interpretable
generalization behavior and the presence of multiple basins on the loss
landscapes of fine tuned text classifiers. Then, I will describe how
manipulating interpretable behaviors during the training process can shed
light on the role of syntactic signals in attention distributions and
generally on how an optimizer’s bias towards early-learned and simple
strategies both helps and hurts language model performance. These results
form the basis of a manifesto for exploring developmental explanations when
researching interpretability and generalization behavior.



*Bio: *Naomi Saphra is a postdoctoral researcher at NYU with Kyunghyun Cho.
She is interested in NLP training dynamics: how models learn to encode
linguistic patterns or other structures and how we can encode useful
inductive biases into the training process. Previously, she earned a PhD
from the University of Edinburgh on Training Dynamics of Neural Language
Models, worked at Google and Facebook, and attended Johns Hopkins and
Carnegie Mellon University. Outside of research, she plays roller derby
under the name Gaussian Retribution, does stand-up comedy, and shepherds
disabled programmers into the world of code dictation.



*Host:* Karen Livescu <klivescu 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 Sun, Feb 26, 2023 at 3:17 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*        Monday, February 27, 2023 at* 11:30 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=8759978c-a0e0-4a2e-9f47-afaf0179b889>*
> )
>
>
>
> *Who: *        Naomi Saphra, NYU
>
>
> ------------------------------
>
> *Title:*         Interpreting Training
>
>
>
> *Abstract:* Interpretability research in NLP often follows a predictable
> pattern—pick an indicator of structure or knowledge such as probe or
> challenge set accuracy, measure that indicator in a fully trained model,
> and assert that this structure or information is integral to how the model
> functions. However, we can achieve a much deeper understanding by
> considering how these indicators emerge from the training process. First,
> this talk will discuss research on the relationship between interpretable
> generalization behavior and the presence of multiple basins on the loss
> landscapes of fine tuned text classifiers. Then, I will describe how
> manipulating interpretable behaviors during the training process can shed
> light on the role of syntactic signals in attention distributions and
> generally on how an optimizer’s bias towards early-learned and simple
> strategies both helps and hurts language model performance. These results
> form the basis of a manifesto for exploring developmental explanations when
> researching interpretability and generalization behavior.
>
>
>
> *Bio: *Naomi Saphra is a postdoctoral researcher at NYU with Kyunghyun
> Cho. She is interested in NLP training dynamics: how models learn to encode
> linguistic patterns or other structures and how we can encode useful
> inductive biases into the training process. Previously, she earned a PhD
> from the University of Edinburgh on Training Dynamics of Neural Language
> Models, worked at Google and Facebook, and attended Johns Hopkins and
> Carnegie Mellon University. Outside of research, she plays roller derby
> under the name Gaussian Retribution, does stand-up comedy, and shepherds
> disabled programmers into the world of code dictation.
>
>
>
> *Host:* Karen Livescu <klivescu 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, Feb 20, 2023 at 5:09 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*        Monday, February 27, 2023 at* 11:30** a**m 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=8759978c-a0e0-4a2e-9f47-afaf0179b889>*
>> )
>>
>>
>> *Who: *        Naomi Saphra, NYU
>>
>>
>> ------------------------------
>> *Title:*         Interpreting Training
>>
>> *Abstract:* Interpretability research in NLP often follows a predictable
>> pattern—pick an indicator of structure or knowledge such as probe or
>> challenge set accuracy, measure that indicator in a fully trained model,
>> and assert that this structure or information is integral to how the model
>> functions. However, we can achieve a much deeper understanding by
>> considering how these indicators emerge from the training process. First,
>> this talk will discuss research on the relationship between interpretable
>> generalization behavior and the presence of multiple basins on the loss
>> landscapes of finetuned text classifiers. Then, I will describe how
>> manipulating interpretable behaviors during the training process can shed
>> light on the role of syntactic signals in attention distributions and
>> generally on how an optimizer’s bias towards early-learned and simple
>> strategies both helps and hurts language model performance. These results
>> form the basis of a manifesto for exploring developmental explanations when
>> researching interpretability and generalization behavior.
>>
>> *Bio: *Naomi Saphra is a postdoctoral researcher at NYU with Kyunghyun
>> Cho. She is interested in NLP training dynamics: how models learn to encode
>> linguistic patterns or other structure and how we can encode useful
>> inductive biases into the training process. Previously, she earned a PhD
>> from the University of Edinburgh on Training Dynamics of Neural Language
>> Models, worked at Google and Facebook, and attended Johns Hopkins and
>> Carnegie Mellon University. Outside of research, she plays roller derby
>> under the name Gaussian Retribution, does standup comedy, and shepherds
>> disabled programmers into the world of code dictation.
>>
>> *Host:* Karen Livescu <klivescu 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/20230227/7578fc9e/attachment-0001.html>