UCL CSML

UCL CSML @ELLISforEurope Unit regrouping @GatsbyUCL, @uclcs and @stats_UCL. We organise the @JumpTrading CSML Seminar Series.

[Advances on Adaptive Experimentation Workshop @aaeworkshop]

Final deadline reminder: applications to AAE close today.

Join us at Gatsby for two days on adaptive experimentation, causal inference, bandits, RL, and sequential decision-making.

Apply: https://t.co/Zar0qWhgA8

[Krishna Balasubramanian @krizna_b]

🚨 🧵 New paper: Finite-particle rates for drifting models.

Drifting trains 1-step generators by moving model μ toward data ν with a conservative or non-conservative velocity field. Consider data on x-axis, model on the y-axis. These 2 fields yield 2 different motions. 1/7

[Arthur Gretton @ArthurGretton]

Your drifting model is secretly a fixed point for the Wasserstein gradient flow on...
...the KL?
...an approximation to the Sinkhorn?
...Is it even a Wasserstein gradient flow at all?

https://t.co/QJLh86Hi0d

@liwenliang @agalashov @JamesTThorn @ValentinDeBort1 @ArnaudDoucet1

[UCL CSML @uclcsml]

Next Wednesday (May 13) at 12:30 pm we’re excited to have Long Tran-Thanh (Warwick) present his work on “Pruning at initialization through the lens of graphon limits”. The seminar will be streamed live at https://t.co/WIZ32HhI2G.

[ELLIS @ELLISforEurope]

Come spend 2 days in adaptive experimentation, causal inference, & online learning at @ucl this June.

Co-organised by @uclcsml, it brings together researchers across theory, methodology, & applications.

📍 London 🇬🇧
📅 18-19 June
⏰ Apply by 28 May
🔗 https://t.co/bzXvXc2m1P

[UCL CSML @uclcsml]

This Wednesday (May 6th) 12:30 pm, we are excited to have Ben Dai (CUHK) present his work on “RankSEG: A consistent ranking-based framework for segmentation”. The seminar will be streamed at https://t.co/OjnGIlTEsi. Please note the event is online only.

[Advances on Adaptive Experimentation Workshop @aaeworkshop]

🚀 Excited to announce the Advances in Adaptive Experimentation (AAE) Workshop!

📅 June 18–19
🔗 https://t.co/Zar0qWhgA8

Join us at @GatsbyUCL in London for two days at the frontier of causal inference 🧩, adaptive experiments 🔁, and bandits/RL 🤖!

[Arthur Gretton @ArthurGretton]

Looking forward to this!

[Weijie Su @weijie444]

We released "The Newton--Muon Optimizer" . We show that Muon is secretly an implicit Newton method, and use this insight to build a better one. 1/n

Paper: https://t.co/Ua54426bWB

[UCL CSML @uclcsml]

This Wedneday (Mar 18th) 12:30 pm, we’re excited to have Tatiana Shavrina (FAIR Meta) present her work on 'Advancing Scientific Research with AI Research Agents'. The seminar will be streamed live at https://t.co/WIZ32HhI2G.

[UCL CSML @uclcsml]

Check out this amazing event organised from UCL ELLIS co-director @fx_briol and his team!

[François-Xavier Briol @fx_briol]

The UCL IMSS Annual Lecture will take place on the 27th April with a keynote from @LesterMackey.

The theme is 'Computational Statistics and Machine Learning', and we will have talks from Alessandro Barp, Paula Cordero Encinar & Po-Ling Loh.

https://t.co/sjLmMokgTx

@stats_UCL

[UCL CSML @uclcsml]

Our next seminar will take place this Wednesday on Jan 14th at 12:30 pm GMT in the Sainsbury Wellcome Centre. Michael Dennis (Google Deepmind) will present his work on “Open-Ended Discovery via Settler-Solver Games”. It will also be streamed live at https://t.co/WIZ32HhI2G

[UCL CSML @uclcsml]

The next seminar is tomorrow (Dec 10th) at 12:30 UK time. Louis Sharrock (UCL) will present on “Tuning-free sampling via optimization on the space of probability measures”. It will be streamed on Zoom at https://t.co/OjnGIlUchQ.

[UCL CSML @uclcsml]

We’d also like to draw your attention to the post NeurIPS event hosted at UCL AI center on Wednesday 10th December 2025, from 2:30 pm onwards. The registration link is https://t.co/aG9hsIPx1p.

[UCL CSML @uclcsml]

The Zoom link is https://t.co/WIZ32HhI2G.

[UCL CSML @uclcsml]

The next seminar is Wednesday (Dec 1) and starts at 12:50 pm (note the unusual starting time). Yanbo Tang from Imperial College London will speak about his recent work on “Stochastic Error Analysis of Numerical Integration in High Dimensions”.

[UCL CSML @uclcsml]

The next seminar is Wednesday (Nov 26) and starts at 12:30pm UK time! Fanghui Liu from University of Warwick is going to talk about “Generalization under suitable model capacities in modern machine learning”! https://t.co/WIZ32HifSe

https://t.co/6IP8252tYT

[UCL CSML @uclcsml]

The next seminar is Wednesday (Nov 17) and starts at 12:30pm UK time! David Siska from University of Edinburgh is going to talk about “Convergence for policy gradient methods for reinforcement learning”! https://t.co/WIZ32HhI2G

https://t.co/6IP8251W9l

[UCL CSML @uclcsml]

The next seminar is Wednesday (Nov 5) and starts at 12:30pm UK time! Zoltan Szabo from LSE is going to talk about “The Minimax Lower Bound of Kernel Stein Discrepancy Estimation”! https://t.co/WIZ32HifSe https://t.co/2mzVuD9632

[UCL CSML @uclcsml]

The next seminar is Wednesday (Nov 5) and starts at 12:30pm UK time! Zoltan Szabo from LSE is going to talk about “The Minimax Lower Bound of Kernel Stein Discrepancy Estimation”! https://t.co/WIZ32HifSe https://t.co/2mzVuD9632