Mis research focuses on the design and analysis of machine learning algorithms for structured data like sequences, trees, and graphs. On the theoretical side, my goal is to advance our understanding of the foundations of data science by identifying essential trade-offs between statistical and computational efficiency. On the applied side, my interests are focused on reinforcement learning and natural language processing. Beyond mainstream machine learning, I am also interested in adjacent areas like automata theory, streaming algorithms, and data privacy.

I am always looking for motivated students with a good mathematical background or advanced hacking skills to work on machine learning problems. I am happy to supervise projects across a wide variety of topics, including (but not limited to!) learning from structured data, privacy-preserving data analysis, machine learning for natural language processing, and reinforcement learning.

Borja Balle joined Lancaster University as a Lecturer in Data Science in 2015. He received his PhD from Universitat Politècnica de Catalunya in 2013 and then spent two years as a postdoctoral fellow at McGill University. He has served as workshops chair for NIPS 2015 and area chair for NIPS 2014, and has organized several workshops on spectral methods of moments (NIPS 2013, ICML 2013, and ICML 2014). His research has been recognized with several awards, including best paper at EACL 2012, best student paper at ICGI 2012, and runner-up for best student paper at NIPS 2012.

- Machine Learning: spectral algorithms, methods of moments, tensor representations, reinforcement learning

- Automata Theory: weighted automata, approximate minimisation, bisimulation and other metrics

- Data Privacy: differential privacy, secure multi-party computation

Homepage: http://lancaster.ac.uk/~deballep/