🔥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

Apply now! Registration closes tonight. #ProbNumSchool

Stochastic bunnies and stochastic spheres: A function space perspective on stochastic shape evolution Libby Thomas Besnier arxiv.org/abs/2302.05382 A new intrinsic stochastic model for shape evolutions. The stochastics is modelled in a Sobolev space of maps from the ...

Did you know Vector’s new Postdoc Fellow Agustinus Kristiadi moved all the way from Tübingen, Germany to Toronto this past month? Learn more about why he decided to join Vector in his full YouTube interview here🧵👉 youtu.be/ql68hhFZ6vs #VectorResearcherFridays

On my way to #NeurIPS23 for the first time. I’ll be there presenting our work "Riemannian Laplace approximations for Bayesian Neural Networks". Work done together with Pablo Moreno-Muñoz, Søren Hauberg, and Georgios Arvanitidis. I’ll be at poster #1223 on Wednesday from 17pm (Session 4).

On my way 🚨✈️🚨 to NOLA. I'll be presenting our work on scalable implicit VI on Wed from 5pm (#1313). I am also looking for internships for 2024 in fundamental or applied generative modelling and uncertainty quantification. #NeurIPS2023

How can Kronecker-Factored Approximate Curvature (K-FAC) be generalised to modern deep learning architectures like transformers, graph, and convolutional neural networks? Find out in our #NeurIPS2023 spotlight paper! (1/10) arxiv.org/abs/2311.00636

We’ll be presenting our work in poster session 5 (#1214, Thursday 10:45) @ #NeurIPS2023 — Come to chat with us if you want to know more about the role of masking in SSL and its connection with Bayesian principles! ⚖️🔮

Excited to share that our paper on reducing variance in diffusion models with control variates is published at the SPIGM ICML Conference workshop. Come check it out! Thanks a lot to will grathwohl Jes Frellsen @carlhenrikek Michael Riis for the collaboration! openreview.net/pdf?id=YqFIzHA…

Score matching for bridges can be learned without time-reversal arxiv.org/abs/2407.15455 w/ Libby Moritz Schauer We learn grad log p(t,x; T,y) for a target y directly without reversing time by combining score matching with adjoint diffusions (Milstein 2004) that give the

"A tutorial on automatic differentiation with complex numbers" (by Nicholas Krämer): arxiv.org/abs/2409.06752

Heading to Vancouver for NeurIPS to present our paper “On Conditional Diffusion Models for PDE Simulation”. I'll be together with Sasha and Cristiana Diaconu at poster 2500 during Thursday’s late afternoon session. Looking forward exciting discussions and meeting new people!

🛩️ On my way to #NeurIPS2024 and excited to chat about (ML applications of) linear algebra, differentiable programming, and probabilistic numerics! Feel free to DM if you’d like to meet up, hang out, and/or discuss any of these topics 😊

Poster session happening *today* at 4:30 local time. *East* Exhibit Hall. Poster #3511. Looking forward to presenting this work! See you there? 🙂