[Theory] REMINDER: 3/18 Talks at TTIC: Lingxiao Wang, UCLA

[Mary Marre]

*When:*      Thursday, March 18th at* 11:10 am CT*



*Where:*     Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_T9w_VcEMQHOEmzX2YbDu5g>*)



*Who: *       Lingxiao Wang, UCLA


*Title: * Towards Efficient and Effective Privacy-Preserving Machine
Learning

*Abstract:* The past decade has witnessed the fast growth and tremendous
success of machine learning. However, recent studies showed that existing
machine learning models are vulnerable to privacy attacks, such as
membership inference attacks, and thus pose severe threats to personal
privacy. Therefore, one of the major challenges in machine learning is to
learn effectively from enormous amounts of sensitive data without giving up
on privacy. In this talk, I will discuss my efforts in addressing this
challenge for solving two important problems: high-dimensional sparse
learning and nonconvex optimization. I will first introduce a
knowledge-transfer framework that achieves improved privacy and utility
guarantees for privacy-preserving sparse learning approaches. I will then
present an efficient stochastic algorithm for solving nonconvex
optimization problems with privacy guarantees.  Lastly, I will discuss some
ongoing and future research.

*Bio: *Lingxiao Wang is a Ph.D. candidate in the Department of Computer
Science at the University of California, Los Angeles, advised by Professor
Quanquan Gu. Previously he obtained his MS degree in Statistics at the
University of Washington. Lingxiao’s research interests are broadly in
machine learning, including privacy-preserving machine learning, low-rank
matrix learning, high-dimensional graphical models, and federated learning.
He is a recipient of Rising Stars in Data Science (2021) from the
University of Chicago.


*Host:* Nathan Srebro <nati at ttic.edu>





Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Wed, Mar 17, 2021 at 5:03 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Thursday, March 18th at* 11:10 am CT*
>
>
>
> *Where:*     Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_T9w_VcEMQHOEmzX2YbDu5g>*
> )
>
>
>
> *Who: *       Lingxiao Wang, UCLA
>
>
> *Title: * Towards Efficient and Effective Privacy-Preserving Machine
> Learning
>
> *Abstract:* The past decade has witnessed the fast growth and tremendous
> success of machine learning. However, recent studies showed that existing
> machine learning models are vulnerable to privacy attacks, such as
> membership inference attacks, and thus pose severe threats to personal
> privacy. Therefore, one of the major challenges in machine learning is to
> learn effectively from enormous amounts of sensitive data without giving up
> on privacy. In this talk, I will discuss my efforts in addressing this
> challenge for solving two important problems: high-dimensional sparse
> learning and nonconvex optimization. I will first introduce a
> knowledge-transfer framework that achieves improved privacy and utility
> guarantees for privacy-preserving sparse learning approaches. I will then
> present an efficient stochastic algorithm for solving nonconvex
> optimization problems with privacy guarantees.  Lastly, I will discuss some
> ongoing and future research.
>
> *Bio: *Lingxiao Wang is a Ph.D. candidate in the Department of Computer
> Science at the University of California, Los Angeles, advised by Professor
> Quanquan Gu. Previously he obtained his MS degree in Statistics at the
> University of Washington. Lingxiao’s research interests are broadly in
> machine learning, including privacy-preserving machine learning, low-rank
> matrix learning, high-dimensional graphical models, and federated learning.
> He is a recipient of Rising Stars in Data Science (2021) from the
> University of Chicago.
>
>
> *Host:* Nathan Srebro <nati at ttic.edu>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Thu, Mar 11, 2021 at 10:07 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*      Thursday, March 18th at* 11:10 am CT*
>>
>>
>>
>> *Where:*     Zoom Virtual Talk (*register in advance here
>> <https://uchicagogroup.zoom.us/webinar/register/WN_T9w_VcEMQHOEmzX2YbDu5g>*
>> )
>>
>>
>>
>> *Who: *       Lingxiao Wang, UCLA
>>
>>
>> *Title: * Towards Efficient and Effective Privacy-Preserving Machine
>> Learning
>>
>> *Abstract:* The past decade has witnessed the fast growth and tremendous
>> success of machine learning. However, recent studies showed that existing
>> machine learning models are vulnerable to privacy attacks, such as
>> membership inference attacks, and thus pose severe threats to personal
>> privacy. Therefore, one of the major challenges in machine learning is to
>> learn effectively from enormous amounts of sensitive data without giving up
>> on privacy. In this talk, I will discuss my efforts in addressing this
>> challenge for solving two important problems: high-dimensional sparse
>> learning and nonconvex optimization. I will first introduce a
>> knowledge-transfer framework that achieves improved privacy and utility
>> guarantees for privacy-preserving sparse learning approaches. I will then
>> present an efficient stochastic algorithm for solving nonconvex
>> optimization problems with privacy guarantees.  Lastly, I will discuss some
>> ongoing and future research.
>>
>> *Bio: *Lingxiao Wang is a Ph.D. candidate in the Department of Computer
>> Science at the University of California, Los Angeles, advised by Professor
>> Quanquan Gu. Previously he obtained his MS degree in Statistics at the
>> University of Washington. Lingxiao’s research interests are broadly in
>> machine learning, including privacy-preserving machine learning, low-rank
>> matrix learning, high-dimensional graphical models, and federated learning.
>> He is a recipient of Rising Stars in Data Science (2021) from the
>> University of Chicago.
>>
>> *Host:* Nathan Srebro <nati at ttic.edu>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757*
>> *f: (773) 357-6970*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210318/3eb4dc69/attachment-0001.html>