You're reading the public-facing archive of the Category Theory Zulip server.
To join the server you need an invite. Anybody can get an invite by contacting Matteo Capucci at name dot surname at gmail dot com.
For all things related to this archive refer to the same person.
Chetan Vuppulury (Jul 10 2020 at 10:36):Does anyone know what the best place to learn information geometry is? I'm a physics/math major with background in qft and higher categorical stuff. So a more abstract approach (maybe something that works on arbitrary measure spaces instead of finite spaces) would be nice. Thanks!
Javier Prieto (Jul 10 2020 at 13:05):@John Baez has some notes on the topic. I believe the standard reference is Amari and Nagaoka, which I have only skimmed. I've been meaning to learn more about this for a while, so if you find any good reference, please share!
Chetan Vuppulury (Jul 10 2020 at 17:24):I was looking at the book by Ay, Jost, Lê and Schwachhöfer which seems more rigorous.
Chetan Vuppulury (Jul 10 2020 at 17:25):By rigorous, I mean they seem to deal with non-finite measure spaces too.
Peiyuan Zhu (Mar 05 2021 at 01:44):Hi is anyone interested in discussing this topic?
Peter Arndt (Mar 05 2021 at 10:52):I would love to, but I am really short on time. Do you already have a particular topic, or book, or article in mind?
Chetan Vuppulury (Mar 05 2021 at 12:57):I would also like to. I was thinking of Nihat Ay's book
Peiyuan Zhu (Mar 05 2021 at 16:49):Yes. But I’m reading tensor algebra to build the foundation. The book is called fundamentals of tensor calculus for engineering with a primer on smooth manifolds by Muhlich.
Peiyuan Zhu (Mar 05 2021 at 16:49):We can move on to Ay Jost, Amari later on once we’ve mastered tensors.
Peiyuan Zhu (Mar 05 2021 at 16:57):But is this going to be too basic for you guys?
Chetan Vuppulury (Mar 05 2021 at 16:58):I am quite comfortable with the geometry side of things, but not the statistics side.
Peiyuan Zhu (Mar 05 2021 at 17:01):Do you want to talk about it this in Sunday Vancouver time? Which city are you from?
Peiyuan Zhu (Mar 05 2021 at 17:09):I can certainly help with the statistics side.
Peter Arndt (Mar 05 2021 at 23:36):I guess I'm either middle ground or lowest common denominator, knowing only a little statistics and a little differential geometry. Ay et al's book looks tough, but of course that's the kind of thing where it pays off to team up. Somewhat friendlier entry points might be John Baez's blog post series on information geometry and the thesis of Guy Lebanon.
Peter Arndt (Mar 05 2021 at 23:38):To make me look less parasitic: I have to offer some knowledge of information theory...
Chetan Vuppulury (Mar 06 2021 at 00:41):Sunday is difficult for me. How about Monday?
Chetan Vuppulury (Mar 06 2021 at 00:43):Actually, maybe Sunday 5 pm (Vancouver time) or later may work
Peiyuan Zhu (Mar 06 2021 at 01:13):Can we do 7 pm Sunday Vancouver time?
Chetan Vuppulury (Mar 06 2021 at 03:07):That's good with me
Peiyuan Zhu (Mar 06 2021 at 06:38):Awesome. See you then. Peter hope you can make it too.
Peiyuan Zhu (Mar 06 2021 at 06:38):Peiyuan Zhu is inviting you to a scheduled Zoom meeting.
Topic: Peiyuan Zhu's Personal Meeting Room
Join Zoom Meeting
https://us04web.zoom.us/j/4207665475?pwd=U3gxdXJkdjZLN2IwNG8xRExJTTZwQT09
Meeting ID: 420 766 5475
Passcode: KwHp2S