About
 Associate Professor, Initiative for Data & AI, Universidad de Chile
 Coordinator, MDS
 Researcher, CMM & AC3E
Email: my first initial followed by my last name (at) dim (dot) uchile (dot) cl
Upcoming talks

30 March 2022. I will also give a talk on GP and OT at the Causal Inference and Missing Data Group at Inria

29 March 2022. I will give a talk about Gaussian processes and Optimal Transportat the Data Learning Group at Imperial College London. See info here
News (last 6 months)

14 March 2022. Paper accepted at IEEE Access! Modelling neonatal EEG using multioutput Gaussian processes (w/ Víctor Caro, JouHui Ho and Scarlet Witting). IEEEXplore link (open access).

2 March 2022. Paper accepted at MNRAS! Detecting the periodicity of highly irregularly sampled lightcurves with Gaussian processes: the case of SDSSJ025214.67002813.7 (w/ Stefano Covino and Aldo Treves). Author copy.

18 January 2022. Paper accepted at AISTATS 2022! Nonstationary multioutput GP via harmonizable spectral mixtures (w/ Matías Altamirano). This works extends our work on the MOSM kernel to the nonstationary case, the preprint will be up soon and code will be included in MOGPTK.

18 January 2022. Paper accepted at AISTATS 2022! On the interplay between information loss and operation loss in representations for classification (w/ Jorge Silva); this work studies how features affect the relationship between information loss (Shannon) and operation loss (error prob). Extended version is here

January 2022. I will be visiting IRIT during January and February 2022 to work on Machine Learning and Signal Processing  Thanks IRIT, CIMI and Université de Toulouse for inviting me!

November 2021. Applications for our Master of Data Science are open until 31 December 2021  see the programme details here

28 September 2021. I am very happy to announce that our article “Streaming computation of optimal weak transport barycenters” has just been accepted at NeurIPS 2021. See the preprint here

25 September 2021. Two of our articles have been accepted at the IEEELACCI conference. See our preprints on: detecting blue whale calls and Bayesian spectral estimation

1 August 2021. Our article “On machine learning and the replacement of human labour: antiCartesianism versus Babbage’s path” has just been accepted at Springer’s Artificial Intelligence & Society. See it here

1 July 2021. I am happy to announce that I joined the Initiative for Data & AI at U de Chile as an Associate Professor.
Research group
My group is called GAMES (Grupo de Aprendizaje de Máquinas, infErencia y Señales). Luckily enough, and up to a minor permutation, the acronym seems to also work in English as Group of MAchine learning, infErence and Signals. Current members are
 Víctor Caro (MSc, Data Science)
 Diego Canales (MSc, Data Science)
 David Molina (MSc, Mathematical Modelling)
 Sebastián López (MSc, Mathematical Modelling)
 Alonso Letelier (MSc, Mathematical Modelling)
Former members:
 Elsa Cazelles, now CNRS Researcher at IRIT
 Jou Hui Ho, now Data Scientist at Cero.ai
 Taco de Wolff, now Data Scientist at InriaChile
 Matías Altamirano, now Research Engineer at CMM
 Alejandro Cuevas, now Data Scientist at NoiseGrasp
 Mauricio Campos, now Data Scientist at CocaCola
 Gonzalo Ríos, now Senior Data Scientist at NoiseGrasp
 Lerko Araya, now Data Scientist at Liberty Latin America
 Iván Castro, now Data Scientist at Amazon Web Services
 Rodrigo Lara, now Data Scientist at PROSPERiA
 Gabriel Parra, now Data Scientist at AutoFact
Short Bio
Felipe Tobar is an Associate Professor at the Initiative for Data and Artificial Intelligence, Universidad de Chile, and the Coordinator of the Master of Data Science at the same institution. He holds Researcher positions at the Center for Mathematical Modeling and the Advanced Center for Electrical and Electronic Engineering. Prior to joining Universidad de Chile, Felipe was a postdoc at the Machine Learning Group, University of Cambridge, during 2015 and he received a PhD in Signal Processing from Imperial College London in 2014. Felipe’s research interests lie in the interface between Machine Learning and Statistical Signal Processing, including approximate inference, Bayesian nonparametrics, spectral estimation, optimal transport and Gaussian processes.
Photos: Color, Colorlowres, BW, BWlowres