Rough landscapes and glass dynamics: from inference to machine learning

15 ottobre 2020      Orario:   16.30

Abstract: The realm of statistical mechanics has been enlarged to describe systems, such as glass forming materials, where structural disorder plays the predominant role. Interestingly the spectrum of applications of this new physics goes much beyond the scope of condensed matter and extends to the currently booming field of data science. In this colloquium I will focus on the challenge of signal-reconstruction from noisy collections of data, omnipresent in machine learning applications and in classical inference problems. By leveraging tools and ideas from glass physics, I will show how we can describe, predict, and enhance the performances of algorithms introduced to tackle these reconstruction problems. 

 

Luogo: link Teams

 

https://teams.microsoft.com/dl/launcher/launcher.html?url=%2F_%23%2Fl%2Fmeetup-join%2F19%3Ameeting_ZWVlNTFlYjgtZmM0My00ZmM3LTg3MzYtNTU0NDE2NWQ5MDAy%40thread.v2%2F0%3Fcontext%3D%257b%2522Tid%2522%253a%2522bb064bc5-b7a8-41ec-babe-d7beb3faeb1c%2522%252c%2522Oid%2522%253a%2522a06f55f4-28c0-49fc-8410-10daf4fcbd34%2522%257d%26anon%3Dtrue&type=meetup-join&deeplinkId=0b2497cd-78db-4caf-bf09-9d7363e56b15&directDl=true&msLaunch=true&enableMobilePage=true&suppressPrompt=true

 

Eventuale Collegamento Web:  https://www.fisicastatistica.org/

Relatore: Chiara Cammarota 

Eventuali Note sul Relatore: Università di Roma "La Sapienza", King's College London

e-Mail di Riferimento dell'organizzatore (indispensabile e interno al Dipartimento): raffaella.burioni@unipr.it

Modificato il