dimitri/blog
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add notes on speakers

Browse source
This commit is contained in:
Dimitri Lozeve 2020-05-05 10:26:19 +02:00
parent dddc5f1c39
commit 149d0a0300
4 changed files with 90 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

52
posts/iclr-2020-notes.org
View file

@ -81,9 +81,59 @@ I will be watching the others in the near future.
This talk was fascinating. It is about robotics, and especially how to
design the "software" of our robots. We want to program a robot in a
way that it could work the best it can over all possible domains it
can encounter.
can encounter. I loved the discussion on how to describe the space of
distributions over domains, from the point of view of the robot
factory:
- The domain could be very narrow (e.g. playing a specific Atari game)
or very broad and complex (performing a complex task in an open
world).
- The factory could know in advance in which domain the robot will
evolve, or have a lot of uncertainty around it.
There are many ways to describe a policy (i.e. the software running in
the robot's head), and many ways to obtain them. If you are familiar
with recent advances in reinforcement learning, this talk is a great
occasion to take a step back, and review the relevant background ideas
from engineering and control theory.
Finally, the most important take-away from this talk is the importance
of /abstractions/. Whatever the methods we use to program our robots,
we still need a lot of human insights to give them good structural
biases. There are many more insights, on the cost of experience,
(hierarchical) planning, learning constraints, etc, so I strongly
encourage you to watch the talk!
** Dr. Laurent Dinh, [[https://iclr.cc/virtual_2020/speaker_4.html][Invertible Models and Normalizing Flows]]
This is a talk about an area of ML research I do not know very well,
but very clearly presented. I really like the approach of teaching a
set of methods from a "historical", personal point of view. Laurent
Dinh shows us how he arrived at this topic, what he finds interesting,
in a very personal and relatable manner. This has the double advantage
of introducing us to a topic that he is passionate about, while also
giving us a glimpse of a researcher's process, without hiding the
momentary disillusions and disappointments, but emphasising the great
achievements. Normalizing flows are also very interesting because it
is grounded in strong theoretical results, that brings together a lot
of different methods.
** Profs. Yann LeCun and Yoshua Bengio, [[https://iclr.cc/virtual_2020/speaker_7.html][Reflections from the Turing Award Winners]]
This talk was very interesting, and yet felt very familiar, as if I
already saw a very similar one elsewhere. Especially for Yann LeCun,
who clearly reuses the same slides for many presentations at various
events. They both came back to their favourite subjects:
self-supervised learning for Yann LeCun, and system 1/system 2 for
Yoshua Bengio. All in all, they are very good speakers, and their
presentations are always insightful. Yann LeCun gives a lot of
references on recent technical advances, which is great if you want to
go deeper in the approaches he recommends. Yoshua Bengio is also very
good at broadening the debate around deep learning, and introducing
very important concepts from cognitive science.
** Prof. Michael I. Jordan, [[https://iclr.cc/virtual_2020/speaker_8.html][The Decision-Making Side of Machine Learning: Dynamical, Statistical and Economic Perspectives]]
TODO
* Workshops