[Colloquium] REMINDER: 3/13 TTIC Colloquium: Laura Balzano, University of Michigan

[Mary Marre via Colloquium]

When:     Monday, March 13th at 11:00 a.m.

Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526

Who:       Laura Balzano, University of Michigan


Title:       Finding Low-rank Structure in Messy Data

Abstract: Many results in recent years have focused on how to identify
low-rank structure in high-dimensional data despite missing and corrupted
data. However, it is typically assumed that we make linear measurements of
the low-rank structure and independent noise. In this talk we will discuss
two new directions. In the first, we observe every entry of the matrix
through a single unknown monotonic transformation. This is common in
calibration and quantization problems. We show that matrix completion is
still possible in this context and demonstrate a simple algorithm with an
MSE guarantee. In the second, our vector observations are heteroscedastic,
ie, corrupted one of several noise variances. This is common in problems
like sensor networks or medical imaging, where different measurements of
the same phenomenon are taken with different quality sensing (eg high or
low radiation) and induces within-sample dependence. We prove recovery
results for PCA in this context. We show that recovery for a fixed average
noise variance is maximized when the noise variances are equal, implying
that while average noise variance is often a convenient measure of the
overall quality of the data, it gives an overly optimistic estimate of PCA
performance.


Host: Nathan Srebro <nati at ttic.edu>

For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Sun, Mar 12, 2017 at 6:29 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:     Monday, March 13th at 11:00 a.m.
>
> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Laura Balzano, University of Michigan
>
>
> Title:       Finding Low-rank Structure in Messy Data
>
> Abstract: Many results in recent years have focused on how to identify
> low-rank structure in high-dimensional data despite missing and corrupted
> data. However, it is typically assumed that we make linear measurements of
> the low-rank structure and independent noise. In this talk we will discuss
> two new directions. In the first, we observe every entry of the matrix
> through a single unknown monotonic transformation. This is common in
> calibration and quantization problems. We show that matrix completion is
> still possible in this context and demonstrate a simple algorithm with an
> MSE guarantee. In the second, our vector observations are heteroscedastic,
> ie, corrupted one of several noise variances. This is common in problems
> like sensor networks or medical imaging, where different measurements of
> the same phenomenon are taken with different quality sensing (eg high or
> low radiation) and induces within-sample dependence. We prove recovery
> results for PCA in this context. We show that recovery for a fixed average
> noise variance is maximized when the noise variances are equal, implying
> that while average noise variance is often a convenient measure of the
> overall quality of the data, it gives an overly optimistic estimate of PCA
> performance.
>
>
> Host: Nathan Srebro <nati at ttic.edu>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757 <(773)%20834-1757>*
> *f: (773) 357-6970 <(773)%20357-6970>*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
> On Mon, Mar 6, 2017 at 9:21 PM, Mary Marre <mmarre at ttic.edu> wrote:
>
>> When:     Monday, March 13th at 11:00 a.m.
>>
>> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:       Laura Balzano, University of Michigan
>>
>>
>> Title:       Finding Low-rank Structure in Messy Data
>>
>> Abstract: Many results in recent years have focused on how to identify
>> low-rank structure in high-dimensional data despite missing and corrupted
>> data. However, it is typically assumed that we make linear measurements of
>> the low-rank structure and independent noise. In this talk we will discuss
>> two new directions. In the first, we observe every entry of the matrix
>> through a single unknown monotonic transformation. This is common in
>> calibration and quantization problems. We show that matrix completion is
>> still possible in this context and demonstrate a simple algorithm with an
>> MSE guarantee. In the second, our vector observations are heteroscedastic,
>> ie, corrupted one of several noise variances. This is common in problems
>> like sensor networks or medical imaging, where different measurements of
>> the same phenomenon are taken with different quality sensing (eg high or
>> low radiation) and induces within-sample dependence. We prove recovery
>> results for PCA in this context. We show that recovery for a fixed average
>> noise variance is maximized when the noise variances are equal, implying
>> that while average noise variance is often a convenient measure of the
>> overall quality of the data, it gives an overly optimistic estimate of PCA
>> performance.
>>
>>
>> Host: Nathan Srebro <nati at ttic.edu>
>>
>> For more information on the colloquium series or to subscribe to the
>> mailing list, please see http://www.ttic.edu/colloquium.php
>>
>>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 504*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757 <(773)%20834-1757>*
>> *f: (773) 357-6970 <(773)%20357-6970>*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170313/6df0a9ba/attachment.html>