I'll be at #ICLR2021 today presenting our "Zero-cost NAS" paper. Interested in speeding up neural architecture search four-fold? Come to poster session 2 iclr.cc/Conferences/20…

Join us now at the ICLR poster session! 🧑‍💻 iclr.cc/virtual/2021/p…

Join me at the poster session at 3pm UK time! 🙂

Our DGN paper was accepted as a long oral presentation (top 3%) at the ICML2021 conference of machine learning!! In this paper, we generalize the notion of directions beyond Euclidean spaces arxiv.org/pdf/2010.02863… Saravanan Vincent Létourneau Gabriele Corso Pietro Lio' Will H.

This a great resource for anyone who is interested in getting into efficiency aspects of GNNs. Thanks for putting this together Chaitanya! 😀

We're not *quite* as good at pruning at init as the lottery ticket hypothesis (LTH) says is possible, but we've made a big jump in this work! A good question is: how can we get it to work better for ImageNet? We make progress but there's still work to do here 🙂

Please sign up! Benefits include free registration :-) If you have any questions please feel free to shoot me or Catherine Tong an email using [email protected]