Director, Lead of the Generative Models & Inference team @ #DeepMind Building models for decision making and sciences Prev @EPFL IFT @Polytechnique @fisicaUSP
Nov 23, 2020 • 5 tweets • 1 min read
I see a lot of smug rants on tweeter about ML researchers. "They are not doing X", "don't know Y", "let's show them how to do Z properly".
But the truth is that ML community is extremely diverse in terms of *academic* backgrounds relative to other fields of science/engineering.
People doing ML research today came from a wide range of backgrounds from string theory to psychology and everything in between. So any statement about the community as a whole is naive at best, unless substantiated by evidence.
Aug 13, 2020 • 24 tweets • 12 min read
The Lie group SU(N) is very important in fundamental particle physics as a Gauge symmetry group. Building SU(N) Gauge-equivariant models is key to make ML useful in this field. It was not easy, but WE DID IT!
SU(N) gauge equivariant flows for LatticeQCD: arxiv.org/abs/2008.05456
This work is the result of the most amazing collaboration between @MIT, @nyuniversity and @DeepMind and I couldn't be more thankful and proud to have the opportunity to work with this team.
