Marco Fraccaro

       Ph.D. student

       Cognitive Systems, DTU Compute

       Technical University of Denmark (DTU)

 

       e-mail: marfra at dtu dot dk

 

 

 

 

 

 

Main research interests

·       Machine Learning

·       Bayesian Inference: stochastic and deterministic approximation techniques such as Markov Chain Monte Carlo methods, Sequential Monte Carlo methods, Expectation Propagation and Variational Inference.

·       Deep Learning: using deep neural networks to parameterize flexible probabilistic graphical models.

·       Recommender systems. For a detailed description of the project see this link.

 

If you want to know a bit more about me, you can take a look at my CV or LinkedIn profile.

 

 

Publications

 

A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning [spotlight presentation]
Marco Fraccaro*, Simon Kamronn*, Ulrich Paquet, Ole Winther

Advances in Neural Information Processing Systems 30, NIPS 2017

 

Semi-Supervised Generation with Cluster-aware Generative Models (arXiv, pdf)

Lars Maaløe, Marco Fraccaro, Ole Winther

arXiv:1704.00637, 2017

 

Sequential Neural Models with Stochastic Layers (arXiv, pdf, supplementary, nips, code) [oral presentation]
Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet, Ole Winther

Advances in Neural Information Processing Systems 29, NIPS 2016

arXiv:1605.07571, 2016

 

An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants (arXiv, pdf)
Marco Fraccaro, Ulrich Paquet, Ole Winther

arXiv:1604.01972, 2016

 

An efficient implementation of Riemannian Manifold Hamiltionian Monte Carlo for Gaussian Process Models (pdf)
Ulrich Paquet, Marco Fraccaro

Technical report, 2016

 

Indexable Probabilistic Matrix Factorization for Maximum Inner Product Search (pdf)
Marco Fraccaro, Ulrich Paquet and Ole Winther
The Thirtieth AAAI Conference on Artificial Intelligence, 2016

 

Perturbation Theory for Variational Inference (pdf)
Manfred Opper, Marco Fraccaro, Ulrich Paquet, Alex Susemihl, and Ole Winther
NIPS 2015 Workshop on Advances in Approximate Bayesian Inferences, 2015

 

Learning to Index (pdf)

Marco Fraccaro

Master thesis, Technical University of Denmark, 2014

 

Palm area detection for reliable hand gesture recognition (pdf)
Giulio Marin, Marco Fraccaro, Mauro Donadeo, Fabio Dominio, and Pietro Zanuttigh
Proceedings of IEEE MMSP 2013, Pula, Italy, 2013