Pietro Michiardi, Ph.D.
Campus SophiaTech: 450, route des Chappes - 06410 BIOT
(CS 50193 – 06904 Sophia Antipolis cedex)
Tel: +33.(0)4.93.00.81.45 -- FAX: +33.(0)4.93.00.82.00
Pietro Michiardi received his M.S. in Computer Science from EURECOM and his M.S. in Electrical Engineering
from Politecnico di Torino. Pietro received his Ph.D. in Computer Science
from Telecom ParisTech (former ENST, Paris), and his HDR (Habilitation)
Today, Pietro is a Professor of Computer Science and head of the Data Science Department at EURECOM.
In his work, Pietro blends theory and system research focusing on scalable machine learning algorithms.
Pietro is interested in developing a theoretical understanding of the optimization process underlying many machine
learning methods, in methodological aspects of computationally efficient Bayesian inference approaches,
and their application to industrial domains such as the automotive and the IT infrastructure industries.
In the past, Pietro worked on a wide range of research topics, including: computer networks and their performance
evaluation, applied cryptography, applied game theory, distributed systems for content storage and distribution,
and distributed data management systems.
Short course, Spring semester
Theory and practice of Deep Learning:
- Feed Forward Neural Nets
- Stochastic optimization and loss landscapes
- CNNs, with a gist of Computer Vision
- Sequence Modeling, also beyond RNNs
Algorithmic Machine Learning
Short course, Spring semester
Practical, end-to-end aspects of Machine Learning:
- Data preparation
- Modelling task
- Model validation
- Organized a-la Kaggle: mini-challenges on a variety of application domains
Previous courses: Distributed systems and Cloud Computing
Applied Game Theory (2009-2012), Web Technologies (2005-2011), Applied Algorithm Design (2009-2014)
I've been active in several domains, including computer networks, caching, task scheduling, data management, and cloud computing.
Although these are important fields, in the following list I'm showing only works in the machine learning domain, which has been attracting most of my attention lately.
For the full publication list, please refer to:
- Mita, Graziano; Papotti, Paolo; Filippone, Maurizio; Michiardi, Pietro, LIBRE: Learning Interpretable Boolean Rule Ensembles, to appear in AISTATS, 2020 [Arxiv version]
- Rossi, Simone; Michiardi, Pietro; Filippone, Maurizio, Good Initializations of Variational Bayes for Deep Models, in ICML, 2019 [Arxiv version]
- Tran, Gia-Lac; Bonilla, Edwin; Cunningham, John ; Michiardi, Pietro; Filippone, Maurizio, Calibrating Deep Convolutional Gaussian Processes, in AISTATS, 2019 [Arxiv version]
- Milios, Dimitrios; Camoriano, Raffaello; Michiardi, Pietro; Rosasco, Lorenzo; Filippone, Maurizio, "Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification", in NIPS, 2018 [Arxiv version]
- Domingues, Remi; Michiardi, Pietro; Zouaoui, Jihane; Filippone, Maurizio, "Deep Gaussian Process autoencoders for novelty detection", in Machine Learning 2018
- Domingues, Remi; Filippone, Maurizio; Michiardi, Pietro; Zouaoui, Jihane, "A comparative evaluation of outlier detection algorithms: Experiments and analyses" in Pattern Recognition, 2018
- Cutajar, Kurt; Bonilla, Edwin V.; Michiardi, Pietro; Filippone, Maurizio, "Practical Learning of Deep Gaussian Processes via Random Fourier Features", in Proc. of ICML 2017, [Arxiv version]
- Lulli, Alessandro; Dell’Amico, Matteo; Michiardi, Pietro; Ricci, Laura, "NG-DBSCAN: Scalable Density-Based Clustering for Arbitrary Data", in Proc. of VLDB, 2017