Applied Harmonic Analysis and Machine Learning 2022
At a glance
Instructors
Joan Bruna
Courant Institute & Center for Data Science, NYU
Agnese Seminara
UniGe | DICCA
Alessandro Verri
UniGe | DIBRIS
Rachel Ward
Oden Institute, UT Austin
Duration
1 week
When
From Sep 5 2022 to Sep 9 2022
Where
Important Dates
Application for financial support or contributed talk/poster: July 1
Notifications of acceptance of financial support: by July 31
Registration deadline: July 31
The school will be held in person. Live streaming of the lectures will be arranged for participants unable to travel to Genoa.
Abstract
The school consists of three courses 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.
Partners
Program
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.
Schedule: TBA
Registration fee
There is no registration fee, but participants are required to register before the deadline (July 31).
Application
Please fill in the application form to apply.
Organizers
Filippo De Mari
UniGe | MaLGa & DIMA - filippo.demari@unige.it
Ernesto De Vito
UniGe | MaLGa & DIMA - ernesto.devito@unige.it
Lorenzo Rosasco
UniGe | MaLGa & DIBRIS - lorenzo.rosasco@unige.it
Matteo Santacesaria
UniGe | MaLGa & DIMA - matteo.santacesaria@unige.it
S. Ivan Trapasso
UniGe | MaLGa & DIMA - salvatoreivan.trapasso@unige.it
Silvia Villa
UniGe | MaLGa & DIMA - silvia.villa@unige.it