Gatsby Computational Neuroscience Unit
@GatsbyUCL
We study mathematical principles of learning, perception & action in brains & machines. Funded by Gatsby Charitable Foundation. Also on bluesky & mastodon.
🥳 Congratulations to Rodrigo Carrasco-Davison on passing his PhD viva with minor corrections! 🎉 📜 Principles of Optimal Learning Control in Biological and Artificial Agents.
Representation learning for two-sample testing, at UAI 2025!
I am attending #UAI2025 in Rio with one poster on hypothesis testing. Please come and discuss with us if you also attend the conference! @xunyet @ArthurGretton 📍 Foyer, Room Copacabana A, Room Mar Azul (Wed 23rd Jul 16:00 pm — 18:30 pm) @UncertaintyInAI 📑 A Unified Data…
Come chat about this at the poster @icmlconf, 11:00-13:30 on Wednesday in the West Exhibition Hall #W-902!
How does in-context learning emerge in attention models during gradient descent training? Sharing our new Spotlight paper @icmlconf: Training Dynamics of In-Context Learning in Linear Attention arxiv.org/abs/2501.16265 Led by Yedi Zhang with @Aaditya6284 and Peter Latham
Excited to share new work @icmlconf by Loek van Rossem exploring the development of computational algorithms in recurrent neural networks. Hear it live tomorrow, Oral 1D, Tues 14 Jul West Exhibition Hall C: icml.cc/virtual/2025/p… Paper: openreview.net/forum?id=3go0l… (1/11)
Excited to present this work in Vancouver at #ICML2025 today 😀 Come by to hear about why in-context learning emerges and disappears: Talk: 10:30-10:45am, West Ballroom C Poster: 11am-1:30pm, East Exhibition Hall A-B # E-3409
Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why? Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns. Read on 🔎⏬
Distributional diffusion models with scoring rules at #icml25 Fewer, larger denoising steps using distributional losses! Wednesday 11am poster E-1910 arxiv.org/pdf/2502.02483 @agalashov @ValentinDeBort1 Guntupalli @zhouguangyao @sirbayes @ArnaudDoucet1
Accelerated Diffusion Models via Speculative Sampling, at #icml25 ! at 16:30 Tuesday July 15 poster E-3012 arxiv.org/abs/2501.05370 @ValentinDeBort1 @agalashov @ArnaudDoucet1
(1/6) Can Autoregressive Models (ARMs) go beyond fixed or random generation orders and learn the optimal order to generate new samples? We believe so! We are excited to present our paper, “Learning-Order Autoregressive Models with Application to Molecular Graph Generation,” at…
🎊 Congratulations to Kevin Huang (@KevinHanHuang1) on passing his PhD viva with minor corrections! 🥳 🔖 Universality beyond the classical asymptotic regime
It was a pleasure to welcome work experience students to SWC and @GatsbyUCL this week through the Camden STEAM initiative with @UCLLifeSciences and @CamdenCouncil They explored our labs and learned about the many paths into #Neuroscience Read more ⤵️ sainsburywellcome.org/web/content/pu…
Excited to share our ICML Oral paper on learning dynamics in linear RNNs!🎉🎉
How do task dynamics impact learning in networks with internal dynamics? Excited to share our ICML Oral paper on learning dynamics in linear RNNs! with @ClementineDomi6 @mpshanahan @PedroMediano openreview.net/forum?id=KGOcr…
🥳 Congratulations to Clementine Domine on passing her PhD viva with minor corrections! 🎉 🔖 Balancing Learning Regimes: The Impact of Prior Knowledge on the Dynamics of Neural Representations
Dimitri Meunier, Antoine Moulin, Jakub Wornbard, Vladimir R. Kostic, Arthur Gretton. [stat.ML]. Demystifying Spectral Feature Learning for Instrumental Variable Regression. arxiv.org/abs/2506.10899…
New research shows long-term learning is shaped by dopamine signals that act as partial reward prediction errors. The study in mice reveals how early behavioural biases predict individual learning trajectories. Find out more ⬇️ sainsburywellcome.org/web/blog/long-…
Last but not least of my travel updates: Courtesy of the very kind @Chau9991, I'm giving a talk at 14:30, 27 Jun @NTU_ccds in SG on data augmentation & Gaussian universality, which strings together several works over my PhD. If you're in SG/Lyon the next few weeks, let me know!
Meanwhile, excited to be in #Lyon for #COLT2025, with a co-first author paper (arxiv.org/abs/2502.15752) with the amazing team -- Matthew Mallory and our advisor Morgane Austern! Keywords: Gaussian universality, dependent data, convex Gaussian min-max theorem, data augmentation!
Missing ICML due to visa :'(, but looking forward to share our ICML paper (arxiv.org/abs/2502.05318) as a poster at #BayesComp, Singapore! Work on symmetrising neural nets for schrodinger equation in crystals, with the amazing Zhan Ni, Elif Ertekin, Peter Orbanz and @ryan_p_adams
Composite Goodness-of-fit Tests with Kernels, now out in JMLR! jmlr.org/papers/v26/24-… Test if your distribution comes from ✨any✨ member of a parametric family. Comes in MMD and KSD flavours, and with code. @oscar__key @fx_briol Tamara Fernandez