Lightnews — Scholar-powered news

Arthur Gretton @arthurgretton.bsky.social · 29d

Fantastic news, congratulations!!

1 1

Arthur Gretton @arthurgretton.bsky.social · Sep 5

Thank you for a fantastic conference!

Motonobu Kanagawa @motonobu-kanagawa.bsky.social · Sep 4

Thank you very much @arthurgretton.bsky.social for your great talk!

3

Arthur Gretton @arthurgretton.bsky.social · Aug 11

Sequential kernel embedding for mediated and time-varying dose response curves

Appearing in Bernoulli:
projecteuclid.org/journals/ber...

with preprint here: arxiv.org/abs/2111.03950

...along with code!
github.com/liyuan9988/K...

Rahul Singh, Liyuan Xu

1 6

Arthur Gretton @arthurgretton.bsky.social · Aug 9

Research Fellow position open at @gatsbyucl.bsky.social
to work with me and Jason Hartford on Causality in Biological Systems!

Apply at link, deadline is 27 August:
www.ucl.ac.uk/work-at-ucl/...

UCL – University College London

UCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021).

www.ucl.ac.uk

5 13

Arthur Gretton @arthurgretton.bsky.social · Jul 19

The method accepts draft proposals sequentially - once a proposal is rejected, a maximal coupling is used to obtain a valid sample, and the process repeats.

re "still working with kernels" - see the other ICML 2025 paper, arxiv.org/abs/2502.02483 which uses distributional kernel scoring rules!

3

Arthur Gretton @arthurgretton.bsky.social · Jul 14

Accelerated Diffusion Models via Speculative Sampling, at #icml25 !

16:30 Tuesday July 15 poster E-3012

arxiv.org/abs/2501.05370

@vdebortoli.bsky.social Galashov @arnauddoucet.bsky.social

1 6 25

Arthur Gretton @arthurgretton.bsky.social · Jul 14

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

@vdebortoli.bsky.social
Galashov Guntupalli Zhou
@sirbayes.bsky.social
@arnauddoucet.bsky.social

3 8

Reposted by Arthur Gretton

Rémi Flamary @rflamary.bsky.social · Jun 27

Distributional Reduction paper with H. Van Assel, @ncourty.bsky.social, T. Vayer , C. Vincent-Cuaz, and @pfrossard.bsky.social is accepted at TMLR. We show that both dimensionality reduction and clustering can be seen as minimizing an optimal transport loss 🧵1/5. openreview.net/forum?id=cll...

1 9 33

Arthur Gretton @arthurgretton.bsky.social · Jun 5

Composite Goodness-of-fit Tests with Kernels, now out in JMLR!

www.jmlr.org/papers/v26/2...

Test if your distribution comes from ✨any✨ member of a parametric family. Comes in MMD and KSD flavours, and with code.

@oscarkey.bsky.social @fxbriol.bsky.social Tamara Fernandez

Composite Goodness-of-fit Tests with Kernels

www.jmlr.org

5 19

Arthur Gretton @arthurgretton.bsky.social · May 26

Turns out that overfitting is the right approach when you want to generalize to new tasks!

Dimitri Meunier @dimitrimeunier.bsky.social · May 26

🚨 New paper accepted at SIMODS! 🚨
“Nonlinear Meta-learning Can Guarantee Faster Rates”

arxiv.org/abs/2307.10870

When does meta learning work? Spoiler: generalise to new tasks by overfitting on your training tasks!

Here is why:
🧵👇

Nonlinear Meta-Learning Can Guarantee Faster Rates

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of ...

arxiv.org

15

Reposted by Arthur Gretton

arXiv cs.LG Machine Learning @cslg-bot.bsky.social · May 21

Mattes Mollenhauer, Nicole M\"ucke, Dimitri Meunier, Arthur Gretton: Regularized least squares learning with heavy-tailed noise is minimax optimal https://arxiv.org/abs/2505.14214 https://arxiv.org/pdf/2505.14214 https://arxiv.org/html/2505.14214

1 6 6

Arthur Gretton @arthurgretton.bsky.social · May 6

Looking forward to this!

Diane Larlus @dlarlus.bsky.social · May 5

#PAISS2025 summer school in the Alps with amazing speakers, including @dimadamen.bsky.social @arthurgretton.bsky.social @science4all.org @yann-lecun.bsky.social @gabrielpeyre.bsky.social @claireve.bsky.social and many more

▶️ Apply here: paiss.inria.fr/apply-2025/

Julien Mairal @jmairal.bsky.social · May 5

The PAISS summer school is back with an incredible line of speakers (and more to come). Spread the word !

7

Arthur Gretton @arthurgretton.bsky.social · May 2

Kernel Single Proxy Control for Deterministic Confounding

at #AISTATS25

Proxy causal learning generally requires two proxy variables - a treatment and an outcome proxy. When is it possible to use just one?

arxiv.org/abs/2308.04585

Liyuan Xu

1 2

Arthur Gretton @arthurgretton.bsky.social · May 2

Credal Two-Sample Tests of Epistemic Uncertainty
at #AISTATS25

Compare credal sets: convex sets of prob measures where elements capture aleatoric uncertainty; set represents epistemic uncertainty.

arxiv.org/abs/2410.12921

@slchau.bsky.social Schrab @sejdino.bsky.social @krikamol.bsky.social

4 13

Arthur Gretton @arthurgretton.bsky.social · May 2

Spectral Representation for Causal Estimation with Hidden Confounders
at #AISTATS2025

A spectral method for causal effect estimation with hidden confounders, for instrumental variable and proxy causal learning
arxiv.org/abs/2407.10448

Haotian Sun, @antoine-mln.bsky.social, Tongzheng Ren, Bo Dai

1 3 3

Arthur Gretton @arthurgretton.bsky.social · May 2

Density Ratio-based Proxy Causal Learning Without Density Ratios 🤔

at #AISTATS2025

An alternative bridge function for proxy causal learning with hidden confounders.
arxiv.org/abs/2503.08371
Bozkurt, Deaner, @dimitrimeunier.bsky.social, Xu

4 7

Reposted by Arthur Gretton

Lénaïc Chizat @lenaicchizat.bsky.social · Apr 14

Announcing : The 2nd International Summer School on Mathematical Aspects of Data Science
mathsdata2025.github.io
EPFL, Sept 1–5, 2025

Speakers:
Bach @bachfrancis.bsky.social
Bandeira
Mallat
Montanari
Peyré @gabrielpeyre.bsky.social

For PhD students & early-career researchers
Apply before May 15!

Mathematical Aspects of Data Science

Graduate Summer School - EPFL - Sept. 1-5, 2025

mathsdata2025.github.io

1 24 45

Arthur Gretton @arthurgretton.bsky.social · Apr 22

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
#ICLR25

openreview.net/forum?id=ReI...

NNs
✨better than fixed-feature (kernel, sieve) when target has low spatial homogeneity,
✨more sample-efficient wrt Stage 1

Kim, @dimitrimeunier.bsky.social, Suzuki, Li

3 8

Arthur Gretton @arthurgretton.bsky.social · Apr 22

Deep MMD Gradient Flow Without Adversarial Training
at #ICLR2025

openreview.net/forum?id=Pf8...

Do you have a GAN critic? Then you have a diffusion!

Adaptive MMD gradient flow trained on a forward diffusion, competitive performance on image generation!

Galashov, @vdebortoli.bsky.social

1 3

Arthur Gretton @arthurgretton.bsky.social · Apr 15

Looking forward to this!

NAVER LABS Europe @naverlabseurope.bsky.social · Apr 11

Applications are 📣OPEN📣 for #PAISS2025 THE AI summer school in #Grenoble 1-5 Sept! Speakers so far @yann-lecun.bsky.social @dimadamen.bsky.social @arthurgretton.bsky.social @gabrielpeyre.bsky.social @science4all.org A. Cristia J. Revaud M. Caron J. Carpentier M. Vladimirova ➡️ paiss.inria.fr

2 5

Arthur Gretton @arthurgretton.bsky.social · Mar 27

congratulations!!

1

Reposted by Arthur Gretton

Pierre Alquier @pierrealquier.bsky.social · Mar 12

Our joint paper with Geoffrey Wolfer @gwolfer.bsky.social "Variance-Aware Estimation of the Kernel Mean Embedding" accepted for publication in the Journal of Machine Learning Research 🥳

arxiv.org/abs/2210.06672

Variance-Aware Estimation of Kernel Mean Embedding

An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, prope...

arxiv.org

1 3 29

Arthur Gretton @arthurgretton.bsky.social · Mar 8

Congratulations @lestermackey.bsky.social !!

Michele Guindani @mguindani.bsky.social · Mar 8

Congratulations to @lestermackey.bsky.social for receiving the 2025 COPSS Award! 🎉👏

Lester is currently the Chair of the Section on Bayesian Statistical Sciences (SBSS) of the American Statistical Association.

1 1 4

Reposted by Arthur Gretton

ELLIS @ellis.eu · Mar 6

Hey ELLIS PhD students, need to travel but low on funds? Learn how ELSA can help with that: bit.ly/4kqjyel

#ELLISPhD #MobilityFund #SustainableAI #ProjectsBuildingOnELLIS

Travel the world with ELSA: our Mobility Fund in Action – ELSA

bit.ly

4 21

Reposted by Arthur Gretton

Pierre Alquier @pierrealquier.bsky.social · Mar 5

I already advertised for this document when I posted it on arXiv, and later when it was published.

This week, with the agreement of the publisher, I uploaded the published version on arXiv.

Less typos, more references and additional sections including PAC-Bayes Bernstein.

arxiv.org/abs/2110.11216

1 22 110