Publications


Selected papers appear in bold


Submitted


  • G. Chirco, L. Malagò, and G. Pistone.
    Lagrangian and Hamiltonian Mechanics for Probabilities on the Statistical Manifold.

  • C. Várady, R. Volpi, L. Malagò, and N. Ay.
    Natural Wake-Sleep Algorithm.

  • Papers in International Journals


  • R. Volpi, U. Thakur, and L. Malagò.
    Changing the Geometry of Representations: α-Embeddings for NLP Tasks.
    Entropy 2021, 23, 287, Special Issue Information Geometry III, 2021

  • R. Volpi and L. Malagò.
    Natural Alpha Embeddings.
    Information Geometry, Vol. 3, Issue 2, 2021. [arXiv:1912.02280]

  • H. J. Hortua, L. Malagò, and R. Volpi.
    Constraining the Reionization History using Bayesian Normalizing Flows.
    Machine Learning: Science and Technology, 1 035014, 2020. [arXiv:1911.08508]

  • H. J. Hortua, R. Volpi, D. Marinelli, and L. Malagò.
    Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks.
    Phys. Rev. D 102, 103509, 2020. [arXiv:1911.08508]

  • L. Malagò, L. Montrucchio, and G. Pistone.
    Wasserstein Riemannian Geometry of Positive Definite Matrices.
    Information Geometry, Vol. 1, Issue 2, pp 137-179, 2018

  • L. Malagò and G. Pistone.
    Natural Gradient Flow in the Mixture Geometry of a Discrete Exponential Family.
    Entropy 17(6), Special Issue on Information, Entropy and their Geometric Structures, 4215-4254, 2015

  • L. Malagò and G. Pistone.
    Combinatorial Optimization with Information Geometry: Newton Method.
    Entropy 16(8), Special Issue on Information Geometry, pages 4260-4289, 2014.

  • Papers in Proceedings of International Conferences and Workshops


  • R. Volpi and L. Malagò.
    Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks.
    Proceedings of the 5th Workshop on Representation Learning for NLP (RepL4NLP-2020), pages 61–71

  • A.-I. Albu, A. Enescu, and L. Malagò.
    Tumour Detection in Brain MRIs by Computing Dissimilarities in the Latent Space of a Variational AutoEncoder.
    Proceedings of the Northern Lights Deep Learning Workshop (NLDL2020), Septentrio Academic Publishing, Vol 1, 2020.

  • P. Hlihor, R. Volpi, and L. Malagò.
    Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks.
    Proceedings of the Northern Lights Deep Learning Workshop (NLDL2020), Septentrio Academic Publishing, Vol 1, 2020.

  • L. Malagò and G. Pistone.
    Second-Order Optimization over the Multivariate Gaussian Distribution.
    Geometric Science of Information (GSI), 2015.

  • L. Malagò and G. Pistone.
    Information Geometry of Gaussian Distributions in View of Stochastic Optimization.
    Proceedings of FOGA '15, held on January 17-20, 2015, Aberystwyth, Wales, 2015.

  • L. Malagò and G. Pistone.
    Gradient Flow of the Stochastic Relaxation on a Generic Exponential Family.
    Proceedings of MaxEnt 2014, held on September 21-26, 2014, Château Clos Lucé, Amboise, France, 2014.
    Extra material: [animation]

  • L. Malagò and G. Pistone.
    Optimization via Information Geometry.
    Book of Proceedings of the Seventh International Workshop on Simulation (IWS) held on May 21-25, 2013, in Rimini, Italy, 2014.

  • L. Malagò and M. Matteucci.
    Robust Estimation of Natural Gradient in Optimization by Regularized Linear Regression.
    Geometric Science of Information (GSI), 2013.

  • L. Malagò, M. Matteucci, and G. Pistone.
    Natural Gradient, Fitness Modelling and Model Selection: A Unifying Perspective.
    IEEE Congress on Evolutionary Computation (CEC), 2013.

  • D. Cucci, L. Malagò and M. Matteucci.
    Variable Transformations in Estimation of Distribution Algorithms.
    Parallel Problem Solving from Nature - PPSN XII, Lecture Notes in Computer Science Volume 7491, pages 428--437, 2012.

  • E. Corsano, D. Cucci, L. Malagò, and M. Matteucci.
    Implicit Model Selection based on Variable Transformations in Estimation of Distribution.
    Learning and Intelligent OptimizatioN Conference LION 6, Lecture Notes in Computer Science, pages 360--365, 2012.

  • G. Valentini, L. Malagò, and M. Matteucci.
    Optimization by l1-constrained Markov fitness modelling.
    Learning and Intelligent OptimizatioN Conference LION 6, Lecture Notes in Computer Science, pages 250--264, 2012.

  • L. Malagò, M. Matteucci, and G. Pistone.
    Optimization of pseudo-boolean functions by stochastic natural gradient descent.
    9th Metaheuristics International Conference (MIC), 2011.

  • L. Malagò, M. Matteucci, and G. Valentini.
    Introducing l1-regularized logistic regression in Markov networks based EDAs.
    Evolutionary Computation (CEC), 2011 IEEE Congress on, pages 1581--1588, 2011.

  • L. Malagò, M. Matteucci, and G. Pistone.
    Stochastic natural gradient descent by estimation of empirical covariances.
    Evolutionary Computation (CEC), 2011 IEEE Congress on, pages 949--956, 2011.

  • L. Malagò, M. Matteucci, and G. Pistone.
    Towards the geometry of estimation of distribution algorithms based on the exponential family.
    Proceedings of FOGA '11, pages 230--242, New York, NY, USA, 2011. ACM.

  • G. Valentini, L. Malagò, and M. Matteucci.
    Evoptool: An extensible toolkit for evolutionary optimization algorithms comparison.
    Evolutionary Computation (CEC), 2010 IEEE Congress on, pages 1--8, 2010.

  • Workshop Papers


  • C. Várady, R. Volpi, L. Malagò, and N. Ay.
    Natural Reweighted Wake-Sleep.
    Deep Learning through Information Geometry NeurIPS Worksop, December 12, 2020

  • H. J. Hortúa, R. Volpi, D. Marinelli, L. Malagò.
    Accelerating MCMC algorithms through Bayesian Deep Networks.
    In Machine Learning and the Physical Sciences Workshop at the 34th NeurIPS, December 11, 2020

  • A.-I. Albu, A. Enescu, and L. Malagò.
    Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations.
    KDD Workshop on Applied Data Science for Healthcare, Trustable and Actionable AI for Healthcare, August 24, 2020

  • A.-I. Albu, A. Enescu, and L. Malagò.
    Detection of Tumours in Brain MRIs with Variational AutoEncoders.
    Machine Learning for Pharma and Healthcare Applications ECML PKDD 2020 Workshop, September 14, 2020

  • R. Colț, C-H Varady, R. Volpi and L. Malagò.
    Automatic Feature Extraction for Phonocardiogram Heartbeat Anomaly Detection using WaveNetVAE.
    Machine Learning for Pharma and Healthcare Applications ECML PKDD 2020 Workshop, September 14, 2020

  • H. J. Hortúa, L. Malagò, and R. Volpi.
    Reliable Uncertainties for Bayesian Neural Networks using Alpha-divergences.
    Uncertainty & Robustness in Deep Learning 2020, ICML Workshop, July 17, 2020

  • H. J. Hortúa, R. Volpi, and L. Malagò.
    Parameters Estimation from the 21 cm signal using Variational Inference.
    ICLR 2020 Workshop on Fundamental Science in the era of AI, April 26 2020

  • S. Sârbu, R. Volpi, A. Pește, and L. Malagò.
    Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds.
    ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models, Stockholm, Sweden, 14-15 July 2018.

  • A. Pește, L. Malagò, and S. Sârbu.
    An Explanatory Analysis of the Geometry of Latent Variables Learned by Variational Auto-Encoders.
    NIPS 2017 Workshop on Bayesian Deep Learning, Long Beach, US, 9 December 2017.

  • A. Pește and L. Malagò.
    Towards the Use of Gaussian Graphical Models in Variational Autoencoders.
    ICML 2017 Workshop on Implicit Models, Sydney, Australia, 10 August 2017.

  • L. Malagò and D. Marinelli.
    Synthetic Generation of Local Minima and Saddle Points for Neural Networks.
    ICML 2017 Workskop on Principled Approaches to Deep Learning, Sydney, Australia, 10 August 2017.

  • L. Malagò, Nicolò Cesa-Bianchi, and Jean-Michel Renders.
    Online Active Learning with Strong and Weak Annotators
    .
    NIPS 2014 Workshop on Crowdsourcing and Machine Learning, Montreal, Canada, 13 December 2014.

  • L. Malagò, and G. Pistone.
    Stochastic Relaxation over the Exponential Family: Second-Order Geometry.
    NIPS 2014 Workshop on Optimization for Machine Learning (OPT2014), Montreal, Canada, 12 December 2014.

  • L. Malagò and G. Pistone.
    A note on the border of an exponential family.
    Working paper, Carlo Alberto Notebooks, No. 168. A shorter version of the paper was presented at the SIS 2010 conference in Padova, Italy. [arXiv:1012.0637]

  • L. Malagò, M. Matteucci and G. Pistone.
    Stochastic relaxation as a unifying approach in 0/1 programming.
    NIPS 2009 Workshop on Discrete Optimization in Machine Learning: Submodularity, Sparsity & Polyhedra (DISCML), Whistler, Canada, 2009.

  • L. Malagò, M. Matteucci, and B. Dal Seno.
    An information geometry perspective on estimation of distribution algorithms: boundary analysis.
    Proceedings of the 2008 GECCO conference companion on Genetic and evolutionary computation, GECCO '08, pages 2081--2088, New York, NY, USA, 2008. ACM.

  • Other contributions


  • A. Bonarini, A. Furlan, L. Malagò, D. Marzorati, M. Matteucci, D. Migliore, M. Restelli, and D. G. Sorrenti.
    Milan Robocup Team 2009.
    Robocup International Symposium 2009, Robocup 2009, Graz, Austria, pages 1--8, 2009.

  • R. Barboza, L. Borra, M. B. Criniti, L. Malagò, and M. Rossi.
    IERoKi, Innovative Entertainment Robot for Kids.
    In Multidisciplinarity and Innovation, ASP projects 1, Alta Scuola Politecnica, pages 56--59. Telesma Edizioni, 2007.
    Extra material: [video]


    Back to the homepage