Applied Harmonic Analysis and Machine Learning 2022
At a glance
Courant Institute & Center for Data Science, NYU
UniGe | DICCA
UniGe | DIBRIS
Oden Institute, UT Austin
From Sep 5 2022 to Sep 9 2022
Application for financial support or contributed talk/poster: July 1. Applications for accommodation support after the deadline will be added to a reserve list.
Notifications of acceptance of financial support: by July 31.
Registration deadline: July 31. Late registration is allowed as long as the registration form is accessible.
The school will be held in person. Live streaming of the lectures will be arranged for participants unable to travel to Genoa.
The school consists of three courses and two invited lectures on applied harmonic analysis and machine learning, given by leading experts. Graduate students in Mathematics, Physics, Computer Science and Engineering, as well as postdoctoral fellows and young researchers, are welcome.
Course title: Geometrical aspects of Deep Learning
Instructor: Joan Bruna
Abstract: In this course we will explore the mathematics of deep learning from a geometric perspective. High-dimensional learning captures several approximation, statistical and computational challenges. We will provide a unified description on the current techniques that attempt to draw the line between positive and negative learning results, and in particular we will explore geometric hypothesis spaces that leverage the physical priors of the learning task.
Course title: A tour of reinforcement learning and applications
Instructors: Agnese Seminara & Alessandro Verri
Abstract: The goal of this course is to provide an introduction to reinforcement learning, striking a balance between mathematical formalism and the discussion of real world applications. We will start from the classical framework of optimal control for dynamical systems and discuss the foundations of dynamic programming algorithms to solve Markov Decision Processes. We will derive the Bellman optimality equation and widely used algorithms to find optimal policies (value and policy iteration, Q learning). We will then add complexity by treating the case where the underlying dynamical system is unknown (either the evolution rule, or the current state of the system or both). Finally, we will discuss recent applications of reinforcement learning to biologically inspired navigation, where real agents interact with a complex environment to reach a desired location.
Course title: From random projections to stochastic gradient descent: the “coin flips” that enable large-scale learning
Instructor: Rachel Ward
Abstract: We will give an overview and history of the theory and applications of several crucial randomized embeddings and algorithms which enable modern machine learning methods to operate at large scale, focusing on the Johnson-Lindenstrauss lemma, the randomized singular value decomposition, and stochastic gradient descent.
Giovanna Citti (University of Bologna & Accademia dei Lincei)
Title: Lie symmetries in CNNs and in the visual cortex (abstract)
Matti Lassas (University of Helsinki)
Title: New deep neural networks solving non-linear inverse problems (abstract)
Schedule: the program is available here.
Practical info: useful details (e.g., how to reach the venue, where to eat, tourism info, etc.) can be found in this booklet.
There is no registration fee, but participants are required to register before the deadline (July 31).
Please fill in the application form to register (no confirmation will be sent unless you successfully applied for financial support or contributed talk/poster).
Filippo De Mari
UniGe | MaLGa & DIMA - firstname.lastname@example.org
Ernesto De Vito
UniGe | MaLGa & DIMA - email@example.com
UniGe | MaLGa & DIBRIS - firstname.lastname@example.org
UniGe | MaLGa & DIMA - email@example.com
S. Ivan Trapasso
UniGe | MaLGa & DIMA - firstname.lastname@example.org
UniGe | MaLGa & DIMA - email@example.com