[Colloquium] REMINDER: 1/17 Talks at TTIC: Thodoris Lykouris, Cornell University

[Mary Marre via Colloquium]

When:     Thursday, January 17th at *11:00 am*

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

Who:       Thodoris Lykouris, Cornell University


*Title*:        Adaptive Decision Making in a Data-Driven Society

*Abstract*:  The emergence of online marketplaces has largely transformed
many areas such as transportation, shopping, hospitality, and
entertainment. These platforms have access to vast amounts of data which
enables them to optimize the services they provide. In this talk, I will
underline common challenges that all these platforms encounter, and focus
on two that arise when platforms aim to learn effectively from sequential
requests at the face of uncertainty. In particular, I will tackle a
significant hurdle in this process: data may be corrupted and the platforms
need to employ learning techniques that are robust to this corruption. I
will then briefly talk about how platforms can avoid over-exploration when
dealing with complex sequential learning settings. I will conclude the talk
by highlighting some of my work on other aspects of adaptive decision
making that arise in this theme, and broadly discussing the role of theory
in this data-driven society.


*Host:*  Avrim Blum <Avrim at ttic.edu>





On Thu, Jan 10, 2019 at 5:14 PM Mary Marre <mmarre at ttic.edu> wrote:

> When:     Thursday, January 17th at *11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Thodoris Lykouris, Cornell University
>
>
> *Title*:        Adaptive Decision Making in a Data-Driven Society
>
> *Abstract*:  The emergence of online marketplaces has largely transformed
> many areas such as transportation, shopping, hospitality, and
> entertainment. These platforms have access to vast amounts of data which
> enables them to optimize the services they provide. In this talk, I will
> underline common challenges that all these platforms encounter, and focus
> on two that arise when platforms aim to learn effectively from sequential
> requests at the face of uncertainty. In particular, I will tackle a
> significant hurdle in this process: data may be corrupted and the platforms
> need to employ learning techniques that are robust to this corruption. I
> will then briefly talk about how platforms can avoid over-exploration when
> dealing with complex sequential learning settings. I will conclude the talk
> by highlighting some of my work on other aspects of adaptive decision
> making that arise in this theme, and broadly discussing the role of theory
> in this data-driven society.
>
>
> *Host:*  Avrim Blum <Avrim at ttic.edu>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *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/colloquium/attachments/20190116/6ee06379/attachment.html>