Introduction Statistics and computation has sold out. The event is being recorded and live streamed, through our YouTube channel.
Recent years have witnessed an increased cross-fertilisation between the fields of statistics and computer science. In the era of Big Data, statisticians are increasingly facing the question of guaranteeing prescribed levels of inferential accuracy within certain time budget. On the other hand, computer scientists are progressively modelling data as noisy measurements coming from an underlying population, exploiting the statistical regularities of the data to save on computation.
This cross-fertilisation has led to the development and understanding of many of the algorithmic paradigms that underpin modern machine learning, including gradient descent methods and generalisation guarantees, implicit regularisation strategies, high-dimensional statistical models and algorithms.
About the event
This event will bring together experts to talk about advances at the intersection of statistics and computer science in machine learning. This two-day conference will focus on the underlying theory and the links with applications, and will feature 12 talks by leading international researchers.
The intended audience is faculty, postdoctoral researchers and Ph.D. students from the UK/EU, in order to introduce them to this area of research and to the Turing.
DAY 1 (MONDAY) AGENDA
10:30 – 10:35 Introduction and welcome
Patrick Rebeschini, The Alan Turing Institute and University of Oxford
10:35 – 11:20 Implicit regularization for general norms and errors
Lorenzo Rosasco, Massachusetts Institute of Technology
11:20 – 12:05 Can learning theory resist deep learning?
Francis Bach, INRIA
12:05 – 13:15 Lunch
13:15 – 14:00 A function space view of overparameterized neural networks
Rebecca Willet, University of Chicago
14:00 – 14:45 Benign overfitting
Peter Bartlett, University of California, Berkley
14:45 – 15:15 Refreshment break
15:15 – 16:00 Fast and optimal low-rank tensor regression via importance
Garvesh Raskutti, University of Wisconsin-Madison
16:00 – 16:45 Big data is low rank
Madeleine Udell, Cornell University
16:45 – 17:00 Event summary, day 1
Quentin Berthet, The Alan Turing Institute and Google
17:00 – 18:30 Poster session and drinks reception
18:30 Event close
DAY 2 (TUESDAY) AGENDA
The British Library
10:30 – 10:35 Introduction and welcome
Ramji Venkataramanan, The Alan Turing Institute and University of
Cambridge
10:35 – 11:20 Data-driven regularisation for solving inverse problems
Carola-Bibiane Schönlieb, The Alan Turing Institute and University of
Cambridge
11:20 – 12:05 Statistical Physics and Learning
Florent Krzakala, Sorbonne Université and Ecole Normale Superieure
12:05 – 13:15 Lunch
13:15 – 14:00 Learning from ranks, learning to rank
Jean-Philippe Vert, Google Brain and Mines ParisTech
14:00 – 14:45 Approximate cross validation for large data and high dimensions
Tamara Broderick, Massachusetts Institute of Technology
14:45 – 15:15 Refreshment break
15:15 – 16:00 From causal inference to autoencoders, memorization and gene
regulation
Caroline Uhler, Massachusetts Institute of Technology
16:00 – 16:45 Does learning require memorization? A short tale about a long
tail
Vitaly Feldman, Google Research, Brain Team
16:45 – 17:15 Event summary, day 2
Varun Kanade, The Alan Turing Institute and University of Oxford
17:15 Event close
0 Comments