From kirthevasankandasamy at gmail.com  Mon Apr  3 12:12:40 2017
From: kirthevasankandasamy at gmail.com (Kirthevasan Kandasamy)
Date: Mon, 3 Apr 2017 12:12:40 -0400
Subject: Fwd: Thesis Proposal - 4/6/17 - Kirthevasan Kandasamy - Tuning
 Hyper-parameters without Grad Students: Scaling up Bandit Optimisation
In-Reply-To: <3efac583-d00e-d878-515b-249d202ee6b1@cs.cmu.edu>
References: <3efac583-d00e-d878-515b-249d202ee6b1@cs.cmu.edu>
Message-ID: <CAB-GCq7dtKzuYQdQgnKDSVzKL3NFw9z3Wq00HhxiFrSDZPNxPQ@mail.gmail.com>

Hi all,

I'll be proposing this Thursday at noon. Feel free to drop by.

-kirthevasan

Sent from my phone. Please excuse brevity.
---------- Forwarded message ----------
From: "Diane Stidle" <diane+ at cs.cmu.edu>
Date: Mar 27, 2017 14:17
Subject: Thesis Proposal - 4/6/17 - Kirthevasan Kandasamy - Tuning
Hyper-parameters without Grad Students: Scaling up Bandit Optimisation
To: "ml-seminar at cs.cmu.edu" <ML-SEMINAR at cs.cmu.edu>, "zoubin at eng.cam.ac.uk"
<zoubin at eng.cam.ac.uk>
Cc:

*Thesis Proposal*

Date: 4/6/17
Time 12:00pm
Place: 6121 GHC
Speaker: Kirthevasan Kandasamy

Title: Tuning Hyper-parameters without Grad Students: Scaling up Bandit
Optimisation
Abstract:
In many scientific and engineering applications, we are tasked with
optimising a black-box function which is expensive to evaluate due to
computational or economic reasons. In *bandit optimisation*, we
sequentially evaluate a noisy function with the goal of identifying its
optimum in as few evaluations as possible. Some applications include tuning
the hyper-parameters of machine learning algorithms, on-line advertising,
optimal policy selection in robotics and maximum likelihood inference in
simulation based scientific models. Today, these problems face new
challenges due to increasingly expensive evaluations and the need to
perform these tasks in high dimensional spaces. At the same time, there are
new opportunities that have not been exploited before. We may have the
flexibility to approximate the expensive function by investing less
resources per evaluation. We can also carry out several evaluations
simultaneously, say via parallel computing or by concurrently conducting
multiple experiments in the real world. In this thesis, we aim to tackle
these and several other challenges to meet emerging demands in large scale
bandit applications. We develop methods with theoretical underpinnings and
which also enjoy good empirical performance.

Thesis Committee:
Barnab?s P?czos (Co-Chair)
Jeff Schneider (Co-Chair)
Aarti Singh
Zoubin Ghahramani (University of Cambridge)

Link to draft document:  cs.cmu.edu/~kkandasa/docs/proposal.pdf
<http://cs.cmu.edu/%7Ekkandasa/docs/proposal.pdf>

-- 
Diane Stidle
Graduate Programs Manager
Machine Learning Department
Carnegie Mellon Universitydiane at cs.cmu.edu412-268-1299 <(412)%20268-1299>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-research/attachments/20170403/e07b98de/attachment.html>

From kandasamy at cmu.edu  Wed Apr  5 20:05:15 2017
From: kandasamy at cmu.edu (Kirthevasan Kandasamy)
Date: Wed, 5 Apr 2017 20:05:15 -0400
Subject: Fwd: ROOM CHANGE - Thesis Proposal - 4/6/17 - Kirthevasan Kandasamy -
 Tuning Hyper-parameters without Grad Students: Scaling up Bandit
 Optimisation
In-Reply-To: <54f7717b-feaf-cb38-218e-3e5cf8d66eed@cs.cmu.edu>
References: <54f7717b-feaf-cb38-218e-3e5cf8d66eed@cs.cmu.edu>
Message-ID: <CAB-GCq4qOM4XVcBmQNRxqOGucRRBHzn5Ox=hPQK8KBTKaWJoMA@mail.gmail.com>

Hi all,

We changed rooms for the proposal.
It is happening tomorrow at noon at GHC 6115.

samy

---------- Forwarded message ----------
From: Diane Stidle <diane+ at cs.cmu.edu>
Date: Tue, Apr 4, 2017 at 2:03 PM
Subject: ROOM CHANGE - Thesis Proposal - 4/6/17 - Kirthevasan Kandasamy -
Tuning Hyper-parameters without Grad Students: Scaling up Bandit
Optimisation
To: "ml-seminar at cs.cmu.edu" <ML-SEMINAR at cs.cmu.edu>, "zoubin at eng.cam.ac.uk"
<zoubin at eng.cam.ac.uk>


*Thesis Proposal*

Date: 4/6/17
Time 12:00pm
Place: *6115 GHC (Note: Room Change)*
Speaker: Kirthevasan Kandasamy

Title: Tuning Hyper-parameters without Grad Students: Scaling up Bandit
Optimisation
Abstract:
In many scientific and engineering applications, we are tasked with
optimising a black-box function which is expensive to evaluate due to
computational or economic reasons. In *bandit optimisation*, we
sequentially evaluate a noisy function with the goal of identifying its
optimum in as few evaluations as possible. Some applications include tuning
the hyper-parameters of machine learning algorithms, on-line advertising,
optimal policy selection in robotics and maximum likelihood inference in
simulation based scientific models. Today, these problems face new
challenges due to increasingly expensive evaluations and the need to
perform these tasks in high dimensional spaces. At the same time, there are
new opportunities that have not been exploited before. We may have the
flexibility to approximate the expensive function by investing less
resources per evaluation. We can also carry out several evaluations
simultaneously, say via parallel computing or by concurrently conducting
multiple experiments in the real world. In this thesis, we aim to tackle
these and several other challenges to meet emerging demands in large scale
bandit applications. We develop methods with theoretical underpinnings and
which also enjoy good empirical performance.

Thesis Committee:
Barnab?s P?czos (Co-Chair)
Jeff Schneider (Co-Chair)
Aarti Singh
Zoubin Ghahramani (University of Cambridge)

Link to draft document:  cs.cmu.edu/~kkandasa/docs/proposal.pdf
<http://cs.cmu.edu/%7Ekkandasa/docs/proposal.pdf>

-- 
Diane Stidle
Graduate Programs Manager
Machine Learning Department
Carnegie Mellon Universitydiane at cs.cmu.edu412-268-1299 <(412)%20268-1299>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-research/attachments/20170405/ff80363c/attachment.html>