🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We're at #ICML2023 and excited to share our work! Our group and collaborators will be presenting 8 papers at the main conference and 5 papers at the workshops. Check out our ICML Conference schedule below, and please come talk to us and our fantastic collaborators :)

Super stoked to be in Honolulu at #ICML2023 presenting our paper Simplex Random Features! Catch our poster (session 6) and our oral presentation (C1) on Thursday. Come to chat about quasi-Monte Carlo, scalable Transformers and the waves at Waikiki!

Quasi-Monte Carlo Graph Random Features was a v fun project investigating how correlations between random walkers can improve the efficiency of sampling on graphs. I’m not in New Orleans this time round but the excellent Krzysztof Choromanski will be at PS 6! arxiv.org/abs/2305.12470

Really enjoyed writing this piece with Tor Erlend Fjelde and Vincent Dutordoir 🙌 Thanks Michael Albergo Valentin De Bortoli James Thornton for your insightful feedback 👌

Come and find out 1) why your random walks shouldn't be i.i.d., and 2) how you can use them to construct random features for graph node kernels! Krzysztof Choromanski and I will be at poster sessions 2 and 5 😎

Excited about this one! Variance reduction in Monte Carlo is really a multi-marginal optimal transport problem, and treating it as such gives us tools to sample more efficiently in Euclidean and discrete spaces arxiv.org/abs/2405.16541