the website of
Gergely Neu


I am a machine learning researcher mainly interested in online optimization, bandit problems, and reinforcement learning theory. My general research mission is to bring theory and practice closer together by proving theoretical performance guarantees of practical algorithms and making principled learning algorithms more accessible to practicioners. In particular, I am trying to find out whether there exist fundamental trade-offs between computational and information-theoretic efficiency in machine learning.

Postdoctoral researcher
AI group, DTIC
Universitat Pompeu Fabra


C/ Roc Boronat 138
08018 Barcelona

cell: (+34) 658 583 101
You might want to check out my CV to get a better picture of what I've done professionally so far.

If you're not sure about how to pronounce my first name, please check out this page. The short story is that you basically have to forget about pronouncing the "l" (i.e., "ly" pronounces as "y"), and both G's are hard (as in the English word "get").