1 code implementation • 15 Mar 2023 • Louis Saddier, Matteo Marsili
The available liquidity at any time in financial markets falls largely short of the typical size of the orders that institutional investors would trade.
no code implementations • 24 Oct 2022 • Rongrong Xie, Matteo Marsili
We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding.
no code implementations • 1 Feb 2022 • Matteo Marsili, Yasser Roudi
This identifies samples obeying Zipf's law as the most compressed loss-less representations that are optimal in the sense of maximal relevance.
no code implementations • 17 Dec 2021 • Rongrong Xie, Matteo Marsili
We study a generic ensemble of deep belief networks which is parametrized by the distribution of energy levels of the hidden states of each layer.
3 code implementations • 2 Aug 2020 • Clélia de Mulatier, Paolo P. Mazza, Matteo Marsili
These are spin models, with interactions of arbitrary order, that are composed of independent components of minimal complexity (Beretta et al., 2018).
no code implementations • 1 Mar 2019 • Nicola Bulso, Matteo Marsili, Yasser Roudi
We investigate the complexity of logistic regression models which is defined by counting the number of indistinguishable distributions that the model can represent (Balasubramanian, 1997).
1 code implementation • 3 Sep 2018 • Ryan John Cubero, Matteo Marsili, Yasser Roudi
We show that the codes that achieve optimal compression in MDL are critical in a very precise sense.
Methodology Data Analysis, Statistics and Probability
no code implementations • 31 Oct 2017 • Juyong Song, Matteo Marsili, Junghyo Jo
The fraction of inputs that are associated to the same state is a natural measure of similarity and is simply related to the cost in bits required to represent these inputs.
no code implementations • 24 Feb 2017 • Alberto Beretta, Claudia Battistin, Clélia de Mulatier, Iacopo Mastromatteo, Matteo Marsili
We thus found that the complexity (or simplicity) of a model is not determined by the order of the interactions, but rather by their mutual arrangements.
no code implementations • 3 Mar 2016 • Nicola Bulso, Matteo Marsili, Yasser Roudi
We propose a method for recovering the structure of a sparse undirected graphical model when very few samples are available.
no code implementations • 15 Apr 2014 • Fabio Caccioli, Imre Kondor, Matteo Marsili, Susanne Still
Investors who optimize their portfolios under any of the coherent risk measures are naturally led to regularized portfolio optimization when they take into account the impact their trades make on the market.
Portfolio Management Risk Management
2 code implementations • 16 Jan 2001 • Lorenzo Giada, Matteo Marsili
We discuss a new approach to data clustering.
Statistical Mechanics Disordered Systems and Neural Networks