[Statlist] Afonso Bandeira: MADZ+: Weinan E (Princeton) on ``A Mathematical Perspective of Machine Learning'' this Wednesday

Maurer Letizia |et|z|@m@urer @end|ng |rom ethz@ch
Tue Mar 31 10:50:50 CEST 2020


Hi all,

I am very happy to announce Weinan E will speak this Wednesday on the newly created MADZ+ (Math and Data Zurich) seminar, over Zoom. I have heard this particular talk be mentioned a few times, and am particularly excited to finally get to see it. Highly recommend it to everyone.

Seminar: MADZ+
Date: Wednesday, April 1st
Time: 16:00 Zurich time
Place: Seminar will take place through Zoom, invitation is below.
Speaker: Weinan E (Princeton): https://web.math.princeton.edu/~weinan/
Title: A Mathematical Perspective of Machine Learning
Abstract: The heart of modern machine learning is the approximation of high dimensional functions.
Traditional approaches, such as approximation by piecewise polynomials, wavelets, or
other linear combinations of fixed basis functions, suffer from the curse of
dimensionality. We will discuss representations and approximations that overcome
this difficulty, as well as gradient flows that can be used
to find the optimal approximation. We will see that at the continuous level, machine
learning can be formulated as a series of reasonably nice variational and PDE-like problems.
Modern machine learning models/algorithms, such as the random feature and shallow/deep
neural network models, can be viewed as special discretizations of such continuous problems.
At the theoretical level, we will present a framework that is suited for analyzing
machine learning models and algorithms in high dimension, and present results that
are free of the curse of dimensionality.
Finally, we will discuss the fundamental reasons that are responsible for the success of
modern machine learning, as well as the subtleties and mysteries that still remain to be
understood.

IMPORTANT: Some of the talks will be recorded and made public afterwards (provided the speaker is happy with that). While we plan to remove the Questions&Answers part after the talk from the recording, you should know that if you ask a question during the actual talk it might show up in the recording; if something is not clear and you want to ask a question while the speaker is presenting but don't want to show up in the recording write on chat and I can ask it; I'll try to pay attention to the chat while I host (if you don't mind showing on the recording you can interrupt the speaker normally, I'll moderate if needed).

Best,
Afonso

Afonso Bandeira is inviting you to a scheduled Zoom meeting.

Topic: MADZ+ Seminar: Weinan E (4pm Zurich time)
Time: Apr 1, 2020 03:45 PM Zurich

Join Zoom Meeting
https://ethz.zoom.us/j/776255333

Meeting ID: 776 255 333

Dial by your location
        +41 31 528 09 88 Switzerland
        +41 43 210 70 42 Switzerland
        +41 43 210 71 08 Switzerland
        +41 22 591 00 05 Switzerland
        +41 22 591 01 56 Switzerland
        +1 213 338 8477 US (Los Angeles)
        +1 253 215 8782 US
        +1 312 626 6799 US (Chicago)
        +1 470 250 9358 US (Atlanta)
        +1 646 518 9805 US (New York)
        +1 669 219 2599 US (San Jose)
        +1 786 635 1003 US (Miami)
Meeting ID: 776 255 333
Find your local number: https://ethz.zoom.us/u/acW5pAiVRm

Join by SIP
776255333 using zoomcrc.com

Join by H.323
162.255.37.11 (US West)
162.255.36.11 (US East)
221.122.88.195 (China)
115.114.131.7 (India Mumbai)
115.114.115.7 (India Hyderabad)
213.19.144.110 (EMEA)
103.122.166.55 (Australia)
209.9.211.110 (Hong Kong)
64.211.144.160 (Brazil)
69.174.57.160 (Canada)
207.226.132.110 (Japan)
Meeting ID: 776 255 333


Join by Skype for Business
https://ethz.zoom.us/skype/776255333




More information about the Statlist mailing list