Postdoc positions in Deep Learning and Machine Learning

04 October 2017


The Romanian Institute of Science and Technology (RIST) has an opening for 2 postdoc positions, in the context of the DeepRiemann project “Riemannian Optimization Methods for Deep Learning”, funded by European structural funds through the Competitiveness Operational Program (POC 2014-2020). The appointments will be for 1 year renewable, with possible extensions up to 3 years.

The DeepRiemann project aims at the design and analysis of novel training algorithms for Neural Networks in Deep Learning, by applying notions of Riemannian optimization and differential geometry. The task of the training a Neural Network is studied by employing tools from Optimization over Manifolds and Information Geometry, by casting the learning process to an optimization problem defined over a statistical manifold, i.e., a set of probability distributions. The project is highly interdisciplinary, with competences spanning from Machine Learning to Optimization, Deep Learning, Statistics, and Differential Geometry. The objectives of the project are multiple and include both theoretical and applied research, together with industrial activities oriented to transfer knowledge, from the institute to a startup or spin-off of the research group.

The positions will be part of the new Machine Learning and Optimization group, which will be performing research at the intersection of Machine Learning, Stochastic Optimization, Deep Learning, and Optimization over Manifolds, from the unifying perspective of Information Geometry. The group is one of two newly-formed groups in Machine Learning at RIST, where about 20 new postdoctoral research associates and research software developers will be hired between 2016 and 2017.

Jobs Description


The open positions will focus on different and overlapping aspects of the project.

  • - Training of Neural Networks using Riemannian geometries. The postdoctoral researcher will conduct research on the design and implementation of novel first- and second-order methods for the training of feedforward networks, based on non-Euclidean geometric methods. In particular at least three alternative geometries play a role in this context: 1) the Fisher-Rao geometry which adopts the Fisher metric tensor over the space of probability distributions associated to a neural network, 2) the Wasserstein geometry, where the Riemannian metric between probability distribution is computed based on the Wasserstein distance, and 3) other specific geometries for the space of the connection weights, which emerge for instance when a normalization of the weights is applied to the network during training. The research will focus on the design of efficient and scalable training algorithms suitable for the large scale settings.


  • - Information Geometry of Deep Generative Models. The postdoctoral researcher will contribute towards the extension of the geometric framework based on Information Geometry for the analysis and training of generative models in Deep Learning, such as Deep Boltzmann Machines, Variational Auto-Encoders and Generative Adversarial Networks. The research will extend the geometric framework based on the Fisher-Rao metric, as in classical Information geometry, but also take into account alternative geometries, such as the Riemann manifold structure for Neural Networks which emerges from the use of Wasserstein distance between probability distributions. The objective of the research will be the design of novel efficient training algorithms for existing models, as well as the proposal of new types of generative models.


  • - Natural Policy Learning for Deep Reinforcement Learning. The postdoctoral researcher will focus on policy-gradient algorithms in deep reinforcement learning, using methods of Information Geometry. In particular the research will focus on the design of novel methods based on Riemannian gradient, such as the natural actor-critic, where gradients are evaluated with respect to the Fisher-Rao Information metric, as well as on other approaches based on alternative geometries. The analysis will be focused towards the implementation of efficient algorithms in reinforcement learning, able to scale in high-dimensions.

    Desired Qualifications


  • - PhD in machine learning, theoretical computer science, stochastic optimization, statistics, applied mathematics, including fields such as manifold optimization, differential geometry, statistical mechanics, and related fields
  • - Strong publication record
  • - Strong analytical skills, such as problem solving and logical thinking
  • - Enthusiasm to work in a multidisciplinary and international research environment
  • - Good written and oral communication skills in English


Knowledge in Machine Learning is helpful, but not strictly mandatory. Doctoral students close to the competition of their thesis will also be considered.

The positions are available immediately. Applications will be reviewed as they are received.

RIST offers competitive salaries and top-level working conditions. The net salary for these positions will be around 2.190 euro, based on new tax incentives for research and development activities in Romania. Positions are endowed with travel resources. The cost of living in Cluj is significantly lower than in Western Europe or the USA (e.g., it is 1/3 of the cost of living in London, UK).

How to Apply


In order to apply to this position, the candidate should send an email to deepriemann.jobs@rist.ro, mentioning in the subject of the email "DeepRiemann Postdoc Application". The email should include among the attachments:

  • - A cover letter
  • - A complete CV with full list of publications
  • - A short research statement (max 3 pages), which describes your research interests and explain why your skills, knowledge and experience makes you a suitable candidate for one or more of the open positions
  • - The pdfs of 2 selected publications
  • - Name and contact information of up to 3 referees, which will be contacted directly by the institute for a reference letter



Informal inquiries can be sent to Dr. Luigi Malagò [malago@rist.ro], which is the Principal Investigator of the DeepRiemann project.

About the Institute


The Romanian Institute of Science and Technology is a non-governmental, not-for-profit, independent research institute, founded in 2009, with the purpose of offering scientists a place to conduct research in Romania with top working conditions, comparable to those you can find in western Europe. RIST currently performs research on computational and experimental neuroscience, computational intelligence, machine learning, and dynamical systems. The institute in currently undergoing a phase of significant and sustained growth supported by European and Romanian structural funds, with plans for hiring around 20 new scientists and researchers in the next year. The institute has close contacts with the Babeș-Bolyai University, which is the largest university in Romania, and with the Technical University of Cluj-Napoca.

The institute is located in Cluj-Napoca, in the heart of Transylvania, which has been named by Lonely Planet as the top region to visit in 2016. Cluj is a welcoming and innovative city, recently listed as one of the major tech hubs (with a 9% growth per year for IT industry). Cluj has 12 universities, over 70k students every year, and an extremely vibrant startup scene, which has recently named the Silicon Valley of Transylvania.

Cluj is Europe's friendliest city for foreigners, according to a study by the UK Office of National Statistics, and Romania is no. 16 in the Internations best expat destinations of 2016. About 1100 French citizens, 800 Italian citizens and 500 German citizens live in Cluj (source). The city has an international airport, only 8km away from the city center, with flights to more than 30 European destinations.

More information about Cluj: