BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Inaugural Lectures - Prof. Martin Jaggi and Prof. Michael Kapralov
DTSTART:20230524T170000
DTEND:20230524T183000
DTSTAMP:20260924T085449Z
UID:dee7b9de2264a467131ad8592971689a691603f0b6c181e1e2b9c7bc
CATEGORIES:Inaugural lectures - Honorary Lecture
DESCRIPTION:Prof. Martin Jaggi\, Prof. Michael Kapralov\nDate: 24 May 202
 3\n\nProgram: \n\n	17:00-17:05: Introduction by Prof. Rüdiger Urbanke\,
  Dean of the IC School\n	17:05-17:35: Inaugural Lecture Prof. Martin Jagg
 i\n	17:35-17:45: Q & A\n	17:45-17:50: Introduction by Prof. Rüdiger Urba
 nke\, Dean of the IC School\n	17:50-18:20: Inaugural Lecture Prof. Michael
  Kapralov\n	18:20-18:30: Q & A\n	18:30-20:00: Apéritif in the hall outsid
 e SG1 (bottom floor)\n\nLocation:  SG1\n\nRegistration: Click here\n\n
 ****************************************************************\n\nProf. 
 Martin Jaggi\n\nA Brief Journey through Machine Learning and Artificial In
 telligence\n\nAbstract\nAlgorithms that learn from data are fascinating a
 nd have become increasingly skillful\, not only since ChatGPT and image ge
 neration. We will discuss how such machine learning algorithms work\, and 
 how this research topic has evolved over recent years. When learning from 
 increasingly large datasets\, efficient training can become difficult\, an
 d poses privacy risks on personal data. New and improved algorithms are re
 quired to address these challenges\, which is the focus of our research gr
 oup at EPFL.\n \nAbout the speaker\nMartin Jaggi is an Associate Professo
 r at EPFL\, heading the Machine Learning and Optimization Laboratory. Befo
 re joining EPFL\, he was a post-doctoral researcher at ETH Zurich\, at the
  Simons Institute in Berkeley\, and at École Polytechnique in Paris. He e
 arned his PhD in Machine Learning and Optimization from ETH Zurich in 2011
 \, and a MSc in Mathematics also from ETH Zurich. He is a co-founder of EP
 FL's Applied Machine Learning Days\, and a Fellow of the European ELLIS ne
 twork.\n\n****************************************************************
 \n\nProf. Michael Kapralov\n\nSublinear Algorithms\n\nAbstract\nAs the siz
 es of modern datasets grow\, many classical polynomial time\, and sometime
 s even linear time\, algorithms become prohibitively expensive: the input 
 is often too large to be stored in the memory of a single compute node\, i
 s hard to partition among nodes in a cluster to avoid communication bottle
 necks or is very expensive to acquire in the first place. Thus\, processin
 g of such datasets requires a new set of algorithmic tools for computing w
 ith extremely constrained resources. I will talk about sublinear algorithm
 s\, a class of algorithms whose resource requirements are substantially sm
 aller than the size of the input that they operate on\, making them a perf
 ect fit for large data analysis. I will focus on some highlights of our 
 recent results on computing in the sublinear regime\, and then discuss so
 me exciting directions for future work.\n\nAbout the speaker\nMichael Kapr
 alov is an Associate Professor at EPFL’s School of Communication and Com
 puter Sciences. He completed his PhD at Stanford\, then spent two years as
  a postdoc at MIT\, and a year at IBM as a Goldstine Postdoctoral Fellow. 
 Michael is broadly interested in theoretical computer science\, with an em
 phasis on theoretical foundations of big data analysis. Most of his algori
 thmic work is in sublinear algorithms\, where specific directions include 
 streaming\, sketching\, sparse recovery and Fourier sampling.
LOCATION:SG 1138 https://plan.epfl.ch/?room==SG%201138
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR