Reliable and cost-effective large scale machine learning

ongoing

In the last decade, machine learning (ML) has become a fundamental tool with a growing impact in many disciplines, from science to industry. However, nowadays, the scenario is changing: data are exponentially growing compared to the computational resources (post Moore's law era), and ML algorithms are becoming crucial building blocks in complex systems for decision making, engineering, science. Current machine learning is not suitable for the new scenario, both from a theoretical and a practical viewpoint: (a) the lack of cost-effectiveness of the algorithms impacts directly the economic/energetic costs of large scale ML, making it barely affordable by universities or research institutes; (b) the lack of reliability of the predictions affects critically the safety of the systems where ML is employed. To deal with the challenges posed by the new scenario, REAL will lay the foundations of a solid theoretical and algorithmic framework for reliable and cost-effective large scale machine learning on modern computational architectures. In particular, REAL will extend the classical ML framework to provide algorithms with two additional guarantees: (a) the predictions will be reliable, i.e., endowed with explicit bounds on their uncertainty guaranteed by the theory; (b) the algorithms will be cost-effective, i.e., they will be naturally adaptive to the new architectures and will provably achieve the desired reliability and accuracy level, by using minimum possible computational resources. The algorithms resulting from REAL will be released as open-source libraries for distributed and multi-GPU settings, and their effectiveness will be extensively tested on key benchmarks from computer vision, natural language processing, audio processing, and bioinformatics. The methods and the techniques developed in this project will help machine learning to take the next step and become a safe, effective, and fundamental tool in science and engineering for large scale data problems.