[Theory] [Theory Lunch] Jeffrey Negrea, Wednesday 9/28 12:30pm-1:45pm, *JCL 298*

[Antares Chen]

Hi everyone,

Hope the start of your quarter is going well! Theory Lunch is resuming
tomorrow *Wednesday 9/28 12:30pm* in *JCL 298*. Jeffrey Negrea will be
giving our first presentation starting around 1:00pm. It'll last a bit
longer than usual, ending around 1:45. If you're free, consider stopping by
and catching up with friends and colleagues in the theory group over some
lunch!

See you soon,
Antares

************************************************************
**************************

*Date**:* September 28, 2022
*Time: *12:30pm CT
*Location: *JCL 298

*Speaker: **Jeffrey Negrea* <https://utstat.toronto.edu/~negrea/>

*Title: **Adapting to failure of the IID assumption*

*Zoom: *[link
<https://uchicago.zoom.us/j/99171292172?pwd=UlR4ZkY1aXJCdkRBTjJqZGwrR0M0QT09>
]

*Abstract:* Assumptions on data are used to develop prediction methods with
optimistic performance guarantees. Even if these assumptions don’t hold, we
often believe that if our models are “nearly correct”, then our methods
will have performance similar to those optimistic guarantees. How can we
use models that we know to be wrong, but expect to be nearly correct, in a
way that is robust and reliable? In order to provide robustness to the
failure of our models, we must quantify the degree to which our simplifying
models fail to explain observed data, and develop prediction methods that
adapt to the degree of this failure.

In this seminar, I will discuss my work on the canonical problem of
sequential prediction with expert advice, i.e., combining predictions from
a large number of models or experts. We define a continuous spectrum of
relaxations of the IID assumption, with IID data at one extreme and
adversarial data at the other. We develop an online learning method that
adapts to the level of failure of the IID assumption. We quantify the
difficulty of prediction with expert advice in all scenarios along the
spectrum we introduce, demonstrate that the prevailing methods do not adapt
to this spectrum, and present new methods that are adaptively minimax
optimal. More broadly, this work shows that it is possible to develop
methods that are both adaptive and robust: they realize the benefits of the
IID assumption when it holds, without ever compromising performance when
the IID assumption fails, and without having to know the degree to which
the IID assumption fails in advance.

This seminar is based on the following two research papers:
1. https://arxiv.org/abs/2007.06552
2.
https://proceedings.neurips.cc/paper/2021/hash/dcd2f3f312b6705fb06f4f9f1b55b55c-Abstract.html

[Theory Lunch Webpage
<https://urldefense.com/v3/__https://orecchia.net/event/theory-lunch/__;!!BpyFHLRN4TMTrA!pwdRh9yLA-IBD6NCNvREJGd9Nj5jtC6_N-AowF6HSwIQeb1FPAmu0L_tAswwp_F5nRs$>
]
[Theory Lunch Calendar
<https://urldefense.com/v3/__https://calendar.google.com/calendar/u/0/embed?src=c_osgf1c1qemdras8mu7l7pdhjrs@group.calendar.google.com&ctz=America*Chicago__;Lw!!BpyFHLRN4TMTrA!pwdRh9yLA-IBD6NCNvREJGd9Nj5jtC6_N-AowF6HSwIQeb1FPAmu0L_tAsww4XtIRnQ$>
]

************************************************************
**************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220927/d9478be6/attachment-0001.html>