Alessandro Achille PhD student
University of California, Los Angeles
achille at cs.ucla.edu
alexachi
Since Fall 2015, I am a PhD student at the Computer Science department of UCLA, working with Prof. Stefano Soatto in the Vision Lab. My research interests include information theory, variational inference, representation learning, deep learning and their applications to computer vision.
Before coming to UCLA, I obtained a Master in Pure Math at the Scuola Normale Superiore and the University of Pisa, where I studied model theory, algebraic topology, and their intersection with Prof. Alessandro Berarducci. During that period, I have also been a visiting student at the University of Leeds Math department.
Publications

On the Emergence of Invariance and Disentangling in Deep RepresentationsArXiv preprint
@ARTICLE{2017arXiv170601350A, author = {{Achille}, A. and {Soatto}, S.}, title = "{On the Emergence of Invariance and Disentangling in Deep Representations}", journal = {ArXiv eprints}, archivePrefix = "arXiv", eprint = {1706.01350}, primaryClass = "cs.LG", keywords = {Computer Science  Learning, Computer Science  Artificial Intelligence, Statistics  Machine Learning}, year = 2017, month = jun }

Information Dropout: learning optimal representations through noisy computationArXiv preprint
@ARTICLE{2016arXiv161101353A, author = {{Achille}, A. and {Soatto}, S.}, title = "{Information Dropout: learning optimal representations through noisy computation}", journal = {ArXiv eprints}, archivePrefix = "arXiv", eprint = {1611.01353}, primaryClass = "stat.ML", keywords = {Statistics  Machine Learning, Computer Science  Learning, Statistics  Computation}, year = 2016, month = nov }

A VietorisSmale mapping theorem for the homotopy of hyperdefinable setsArXiv preprint
@ARTICLE{2017arXiv170602094A, author = {{Achille}, A. and {Berarducci}, A.}, title = "{A VietorisSmale mapping theorem for the homotopy of hyperdefinable sets}", journal = {ArXiv eprints}, archivePrefix = "arXiv", eprint = {1706.02094}, primaryClass = "math.LO", keywords = {Mathematics  Logic}, year = 2017, month = jun }