🔥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

Bias/Variance is not the same as Approximation/Estimation Gavin Brown, Riccardo Ali. Action editor: Trevor Campbell. openreview.net/forum?id=4TnFb… #losses #classification #loss

Here's a story about one of the most surprising/unexpected papers I've ever published, out in TMLR today. The title is "Bias/Variance is not the same as Approximation/Estimation", written with the outstanding @RiccardoAli1. Paper here: openreview.net/forum?id=4TnFb…

The most surprising paper I've ever published... “Bias/Variance is not the same as Approximation/Estimation”. openreview.net/forum?id=4TnFb… We figured out the precise connection between two seminal results in ML theory... somehow this was overlooked for 50+ years? Computer Science @ The University of Manchester @RiccardoAli1

Presenting at the ICML GRaM Workshop at ICML 2024 workshop our work (with Paulina Kulytė, Haitz Sáez de Ocáriz Borde , Pietro Lio') "Metric Learning for Clifford Group Equivariant Neural Networks"! Do come by to see how category theory can be used to ensure geometric consistency in deep learning

Thank you to everyone who came to the Learning on Graphs Conference 2025 meetup in Oxford yesterday! Also, shoutout to Jacob Bamberger Teo Reu xiaowen dong Michael Bronstein for co-organizing and making this possible! :-)

Riccardo Ali Riccardo Ali & Paulina Kulytė Paulina Kulytė: "Metric Learning for Clifford Group Equivariant Neural Networks" (ICML'24 GRaM) w/ Haitz Sáez de Ocáriz Borde Pietro Lio' proceedings.mlr.press/v251/ali24a.ht…

Introducing All-atom Diffusion Transformers — towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team FAIR Chemistry AI at Meta There are a couple ML ideas which I think are new and exciting in here 👇

Excited to be giving a talk at the Cambridge Wednesday Seminar today at 3pm. Looking forward to sharing ideas and great discussion about equivariance and beyond Thanks Pietro Lio' Riccardo Ali for inviting me! cst.cam.ac.uk/seminars/list/…