[Colloquium] REMINDER: 3/31 Thesis Defense: Pedro Pamplona Savarese, TTIC

[Mary Marre via Colloquium]

*When*:    Monday, March 31st from* 2**pm - 3pm CT*

*Where*:   Talk will be given *live, in-person* at
               TTIC, 6045 S. Kenwood Avenue
               5th Floor, *Room 530*

*Virtually*: via *Zoom*
<https://uchicagogroup.zoom.us/j/95776718712?pwd=henpHX0NzdT3ZXbakSzbMy3uCJz7i1.1>


*Who:  *    Pedro Pamplona Savarese, TTIC


*Title:      *Principled Approximation Methods for Efficient and Scalable
Deep Learning

*Abstract:* Deep learning has achieved unprecedented success across domains
by scaling up model size and training data. However, the computational
costs of modern networks such as foundation models pose increasingly
significant challenges for both training and deployment. Reducing these
costs is a central research problem, yet many efficiency methods are
themselves computationally expensive or even intractable.

In the first part of this talk, we will explore three strategies for
improving efficiency: discovering efficient architectures, enforcing
parameter sparsity, and quantizing networks. Each approach is grounded in
an intractable optimization problem, for which we will discuss novel
approximations that are both efficient and scalable.

In the second part of this talk, we will focus on reducing training costs
through adaptive optimization methods. We will revisit the theoretical
properties of Adam and examine variants that improve both theoretical
guarantees and empirical performance, offering robust alternatives for
large-scale training.

Together, these contributions provide a principled framework for building
scalable and efficient deep networks. By leveraging approximations for
challenging optimization problems, this work addresses some of the most
pressing obstacles in modern deep learning.


*Advisors: *David McAllester, Michael Maire
*Thesis Committee: *David McAllester, Michael Maire and Karen Livescu




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 Thu, Mar 20, 2025 at 5:37 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When*:    Monday, March 31st from* 2**pm - 3pm CT*
>
> *Where*:   Talk will be given *live, in-person* at
>                TTIC, 6045 S. Kenwood Avenue
>                5th Floor, *Room 530*
>
> *Virtually*: via *Zoom*
> <https://uchicagogroup.zoom.us/j/95776718712?pwd=henpHX0NzdT3ZXbakSzbMy3uCJz7i1.1>
>
>
> *Who:  *    Pedro Pamplona Savarese, TTIC
>
>
> *Title: *Principled Approximation Methods for Efficient and Scalable Deep
> Learning
>
> *Abstract:* Deep learning has achieved unprecedented success across
> domains by scaling up model size and training data. However, the
> computational costs of modern networks such as foundation models pose
> increasingly significant challenges for both training and deployment.
> Reducing these costs is a central research problem, yet many efficiency
> methods are themselves computationally expensive or even intractable.
>
> In the first part of this talk, we will explore three strategies for
> improving efficiency: discovering efficient architectures, enforcing
> parameter sparsity, and quantizing networks. Each approach is grounded in
> an intractable optimization problem, for which we will discuss novel
> approximations that are both efficient and scalable.
>
> In the second part of this talk, we will focus on reducing training costs
> through adaptive optimization methods. We will revisit the theoretical
> properties of Adam and examine variants that improve both theoretical
> guarantees and empirical performance, offering robust alternatives for
> large-scale training.
>
> Together, these contributions provide a principled framework for building
> scalable and efficient deep networks. By leveraging approximations for
> challenging optimization problems, this work addresses some of the most
> pressing obstacles in modern deep learning.
>
>
> *Advisors: *David McAllester, Michael Maire
> *Thesis Committee: *David McAllester, Michael Maire and Karen Livescu
>
>
>
>
> 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/colloquium/attachments/20250327/7930a8f1/attachment.html>