105 citations · 199 across the 9 of their papers we have counts for
11 papers
Learning Aggregation Functions
Giovanni Pellegrini, Alessandro Tibo, Paolo Frasconi +2
Learning on sets is increasingly gaining attention in the machine learning community, due to its widespread applicability. Typically, representations over sets are computed by usin…
Classification of cancer pathology reports: a large-scale comparative study
Stefano Martina, Leonardo Ventura, Paolo Frasconi
We report about the application of state-of-the-art deep learning techniques to the automatic and interpretable assignment of ICD-O3 topography and morphology codes to free-text ca…
MARTHE: Scheduling the Learning Rate Via Online Hypergradients
Michele Donini, Luca Franceschi, Massimiliano Pontil +2
We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization. We describe the structure…
Learning and Interpreting Multi-Multi-Instance Learning Networks
Alessandro Tibo, Manfred Jaeger, Paolo Frasconi
We introduce an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentenc…
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
Luca Franceschi, Paolo Frasconi, Saverio Salzo +2
We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel…
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
Luca Franceschi, Riccardo Grazzi, Massimiliano Pontil +2
In (Franceschi et al., 2018) we proposed a unified mathematical framework, grounded on bilevel programming, that encompasses gradient-based hyperparameter optimization and meta-lea…
Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
Tijn Borghuis, Alessandro Tibo, Simone Conforti +3
We describe a system based on deep learning that generates drum patterns in the electronic dance music domain. Experimental results reveal that generated patterns can be employed t…
A Bridge Between Hyperparameter Optimization and Learning-to-learn
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We consider a class of a nested optimization problems involving inner and outer objectives. We observe that by taking into explicit account the optimization dynamics for the inner…
Shift Aggregate Extract Networks
Francesco Orsini, Daniele Baracchi, Paolo Frasconi
We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in ke…
Forward and Reverse Gradient-Based Hyperparameter Optimization
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm s…
Cell identification in whole-brain multiview images of neural activation
Marco Paciscopi, Ludovico Silvestri, Francesco Saverio Pavone +1
We present a scalable method for brain cell identification in multiview confocal light sheet microscopy images. Our algorithmic pipeline includes a hierarchical registration approa…