Pierre-Alexandre Mattei
@pamattei.bsky.social
Research scientist, Inria. Statistical machine learning.
Reposted by Pierre-Alexandre Mattei
Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
September 19, 2025 at 9:13 AM
Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
« Can you train a standard classifier without labels ? » was the question we tried to investigate in this survey. Very happy to see @louisohl.bsky.social ‘s final PhD projet published in ACM CSUR!
Great news: our "Tutorial on discriminative clustering and mutual information" got upgraded from preprint to ACM Computing Surveys publication! (with @pamattei.bsky.social and Frédéric Precioso).
It is available on open access here: dl.acm.org/doi/10.1145/...
It is available on open access here: dl.acm.org/doi/10.1145/...
A Tutorial on Discriminative Clustering and Mutual Information | ACM Computing Surveys
To cluster data is to separate samples into distinctive groups that should ideally
have some cohesive properties. Today, numerous clustering algorithms exist, and their
differences lie essentially in ...
dl.acm.org
September 15, 2025 at 4:17 PM
« Can you train a standard classifier without labels ? » was the question we tried to investigate in this survey. Very happy to see @louisohl.bsky.social ‘s final PhD projet published in ACM CSUR!
Reposted by Pierre-Alexandre Mattei
Is your company interested in reaching Europe's leading AI researchers?
If so, don't worry! There are still plenty of opportunity to support #EurIPS as a sponsor. Sponsorship packages are available and can be further customized if necessary.
More info at: eurips.cc/become-sponsor/
If so, don't worry! There are still plenty of opportunity to support #EurIPS as a sponsor. Sponsorship packages are available and can be further customized if necessary.
More info at: eurips.cc/become-sponsor/
September 1, 2025 at 8:12 AM
Is your company interested in reaching Europe's leading AI researchers?
If so, don't worry! There are still plenty of opportunity to support #EurIPS as a sponsor. Sponsorship packages are available and can be further customized if necessary.
More info at: eurips.cc/become-sponsor/
If so, don't worry! There are still plenty of opportunity to support #EurIPS as a sponsor. Sponsorship packages are available and can be further customized if necessary.
More info at: eurips.cc/become-sponsor/
Reposted by Pierre-Alexandre Mattei
📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS 2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. [1/3]
August 12, 2025 at 11:46 AM
📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS 2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. [1/3]
Reposted by Pierre-Alexandre Mattei
Estimating a set’s size from uniform (or o/w well-defined) samples is a classical problem, with two well-studied extremes: min structure (birthday problem), max structure (German tank problem). A framework interpolating between them, amongst other things:
arxiv.org/abs/2508.05901
arxiv.org/abs/2508.05901
Estimating the size of a set using cascading exclusion
Let $S$ be a finite set, and $X_1,\ldots,X_n$ an i.i.d. uniform sample from $S$. To estimate the size $|S|$, without further structure, one can wait for repeats and use the birthday problem. This requ...
arxiv.org
August 11, 2025 at 9:12 PM
Estimating a set’s size from uniform (or o/w well-defined) samples is a classical problem, with two well-studied extremes: min structure (birthday problem), max structure (German tank problem). A framework interpolating between them, amongst other things:
arxiv.org/abs/2508.05901
arxiv.org/abs/2508.05901
Reposted by Pierre-Alexandre Mattei
I am pleased to announce that together with some friends, we are organising a workshop on Non-Reversible MCMC Sampling, taking place at Newcastle University from 8–10 September 2025.
Details on the programme and registration can be found at the workshop website (sites.google.com/view/probai-...).
Details on the programme and registration can be found at the workshop website (sites.google.com/view/probai-...).
July 24, 2025 at 11:28 AM
I am pleased to announce that together with some friends, we are organising a workshop on Non-Reversible MCMC Sampling, taking place at Newcastle University from 8–10 September 2025.
Details on the programme and registration can be found at the workshop website (sites.google.com/view/probai-...).
Details on the programme and registration can be found at the workshop website (sites.google.com/view/probai-...).
Reposted by Pierre-Alexandre Mattei
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
July 16, 2025 at 10:01 PM
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
Reposted by Pierre-Alexandre Mattei
📢 Present your NeurIPS paper in Europe!
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
July 16, 2025 at 11:00 PM
📢 Present your NeurIPS paper in Europe!
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Reposted by Pierre-Alexandre Mattei
Alright, people, let's be honest: GenAI systems are everywhere, and figuring out whether they're any good is a total mess. Should we use them? Where? How? Do they need a total overhaul?
(1/6)
(1/6)
June 15, 2025 at 12:20 AM
Alright, people, let's be honest: GenAI systems are everywhere, and figuring out whether they're any good is a total mess. Should we use them? Where? How? Do they need a total overhaul?
(1/6)
(1/6)
Reposted by Pierre-Alexandre Mattei
Pour que les Français acceptent la nécessaire consolidation des finances publiques, il faut que la charge en soit équitablement répartie. Ma tribune @lemonde avec O. Blanchard et G. Zucman.
www.lemonde.fr/idees/articl...
www.lemonde.fr/idees/articl...
Olivier Blanchard, Jean Pisani-Ferry et Gabriel Zucman : « Nous partageons le constat qu’un impôt plancher sur les grandes fortunes est le plus efficace face à l’inégalité fiscale »
TRIBUNE. Le dispositif cible les centimillionnaires qui mettent en place des schémas d’optimisation pour échapper à l’impôt. Il ne fait que mettre en conformité nos lois fiscales avec le principe d’ég...
www.lemonde.fr
June 11, 2025 at 5:48 AM
Pour que les Français acceptent la nécessaire consolidation des finances publiques, il faut que la charge en soit équitablement répartie. Ma tribune @lemonde avec O. Blanchard et G. Zucman.
www.lemonde.fr/idees/articl...
www.lemonde.fr/idees/articl...
The Journées de Statistique of the @statfr.bsky.social is one of my favorite conferences! It started with the Le Cam award being given to Judith Rousseau for her work on Bayesian asymptotics. Judith talked about semiparametric Bernstein-von Mises theorems and her new love for the Bayesian bootstrap.
June 2, 2025 at 8:59 AM
The Journées de Statistique of the @statfr.bsky.social is one of my favorite conferences! It started with the Le Cam award being given to Judith Rousseau for her work on Bayesian asymptotics. Judith talked about semiparametric Bernstein-von Mises theorems and her new love for the Bayesian bootstrap.
Reposted by Pierre-Alexandre Mattei
New preprint!
Introducing "A tutorial on discriminative clustering and mutual information"
With @pamattei.bsky.social and Frédéric Precioso.
arxiv.org/abs/2505.04484
This preprint covers the history of discriminative clustering with pedagogical intents.
Introducing "A tutorial on discriminative clustering and mutual information"
With @pamattei.bsky.social and Frédéric Precioso.
arxiv.org/abs/2505.04484
This preprint covers the history of discriminative clustering with pedagogical intents.
A Tutorial on Discriminative Clustering and Mutual Information
To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in ...
arxiv.org
May 12, 2025 at 8:19 AM
New preprint!
Introducing "A tutorial on discriminative clustering and mutual information"
With @pamattei.bsky.social and Frédéric Precioso.
arxiv.org/abs/2505.04484
This preprint covers the history of discriminative clustering with pedagogical intents.
Introducing "A tutorial on discriminative clustering and mutual information"
With @pamattei.bsky.social and Frédéric Precioso.
arxiv.org/abs/2505.04484
This preprint covers the history of discriminative clustering with pedagogical intents.
Reposted by Pierre-Alexandre Mattei
We are organising EWRL in Tübingen in September. We are working on the program and we will soon be able to make first announcements. Stay tuned, follow @ewrl18.bsky.social
Mark your calendars, EWRL is coming to Tübingen! 📅
When? September 17-19, 2025.
More news to come soon, stay tuned!
When? September 17-19, 2025.
More news to come soon, stay tuned!
April 8, 2025 at 2:03 PM
We are organising EWRL in Tübingen in September. We are working on the program and we will soon be able to make first announcements. Stay tuned, follow @ewrl18.bsky.social
Reposted by Pierre-Alexandre Mattei
and what a great #PhD summer school!
Thanks @jesfrellsen.bsky.social @pamattei.bsky.social and @jmtomczak.bsky.social for organizing it (and having me).
Amazing talks, interactions, location and food 💙
Thanks @jesfrellsen.bsky.social @pamattei.bsky.social and @jmtomczak.bsky.social for organizing it (and having me).
Amazing talks, interactions, location and food 💙
Great quote (and great talk) by @nolovedeeplearning.bsky.social at #GeMMS2025
April 4, 2025 at 3:01 PM
and what a great #PhD summer school!
Thanks @jesfrellsen.bsky.social @pamattei.bsky.social and @jmtomczak.bsky.social for organizing it (and having me).
Amazing talks, interactions, location and food 💙
Thanks @jesfrellsen.bsky.social @pamattei.bsky.social and @jmtomczak.bsky.social for organizing it (and having me).
Amazing talks, interactions, location and food 💙
Today was the first day of invited talks of GeMSS/Statlearn @gemssai.bsky.social with great lectures by @glouppe.bsky.social and Yingzhen Li in the morning…
April 3, 2025 at 9:18 PM
Today was the first day of invited talks of GeMSS/Statlearn @gemssai.bsky.social with great lectures by @glouppe.bsky.social and Yingzhen Li in the morning…
Reposted by Pierre-Alexandre Mattei
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235
January 29, 2025 at 4:15 PM
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235
We’re organizing once again the Gznerative Modeling Summer school this spring on the Côte d’Azur, merged for the occasion with SFdS’s Statlearn!
Applications are open!
Applications are open!
Excited about
🎓 Generative Modeling Summer School / Statlearn
🗓️ Mar 31 - Apr 4, 2025, France
ℹ️ gemss.ai
🎟️ Deadline: Jan 27, 2025
🧑🏫 Yingzhen Li, @stephanmandt.bsky.social, Aude Sportisse, Anna Korba, @glouppe.bsky.social, @jesfrellsen.bsky.social, @pamattei.bsky.social, @jmtomczak.bsky.social, TBA
🎓 Generative Modeling Summer School / Statlearn
🗓️ Mar 31 - Apr 4, 2025, France
ℹ️ gemss.ai
🎟️ Deadline: Jan 27, 2025
🧑🏫 Yingzhen Li, @stephanmandt.bsky.social, Aude Sportisse, Anna Korba, @glouppe.bsky.social, @jesfrellsen.bsky.social, @pamattei.bsky.social, @jmtomczak.bsky.social, TBA
Generative Modeling Summer School (GeMSS)
gemss.ai
January 10, 2025 at 3:27 PM
We’re organizing once again the Gznerative Modeling Summer school this spring on the Côte d’Azur, merged for the occasion with SFdS’s Statlearn!
Applications are open!
Applications are open!
Reposted by Pierre-Alexandre Mattei
A happy author discovering the first hard copies
December 21, 2024 at 3:24 PM
A happy author discovering the first hard copies
Reposted by Pierre-Alexandre Mattei
Heading to Vancouver for NeurIPS to present our paper “On Conditional Diffusion Models for PDE Simulation”. I'll be together with Sasha and Cristiana at poster 2500 during Thursday’s late afternoon session. Looking forward exciting discussions and meeting new people! 🥸🥸
neurips.cc/virtual/2024...
neurips.cc/virtual/2024...
December 9, 2024 at 4:48 PM
Heading to Vancouver for NeurIPS to present our paper “On Conditional Diffusion Models for PDE Simulation”. I'll be together with Sasha and Cristiana at poster 2500 during Thursday’s late afternoon session. Looking forward exciting discussions and meeting new people! 🥸🥸
neurips.cc/virtual/2024...
neurips.cc/virtual/2024...
Reposted by Pierre-Alexandre Mattei
Sad news. Jacques Roubaud, mathematician, poet, member of the OuLiPo, passed away today.
en.wikipedia.org/wiki/Jacques...
en.wikipedia.org/wiki/Jacques...
Jacques Roubaud - Wikipedia
en.wikipedia.org
December 5, 2024 at 2:02 PM
Sad news. Jacques Roubaud, mathematician, poet, member of the OuLiPo, passed away today.
en.wikipedia.org/wiki/Jacques...
en.wikipedia.org/wiki/Jacques...
Reposted by Pierre-Alexandre Mattei
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
Reposted by Pierre-Alexandre Mattei
👩🎓👨🎓 Internship offers (1st step to PhD program) in my group:
team.inria.fr/soda/job-off...
Topics:
◼ Health AI & causality, accounting for censoring (for people who love health impact)
◼ Foundation models for tabular learning (for people into bigger models)
Come work with us!
team.inria.fr/soda/job-off...
Topics:
◼ Health AI & causality, accounting for censoring (for people who love health impact)
◼ Foundation models for tabular learning (for people into bigger models)
Come work with us!
November 27, 2024 at 1:44 PM
👩🎓👨🎓 Internship offers (1st step to PhD program) in my group:
team.inria.fr/soda/job-off...
Topics:
◼ Health AI & causality, accounting for censoring (for people who love health impact)
◼ Foundation models for tabular learning (for people into bigger models)
Come work with us!
team.inria.fr/soda/job-off...
Topics:
◼ Health AI & causality, accounting for censoring (for people who love health impact)
◼ Foundation models for tabular learning (for people into bigger models)
Come work with us!
Opening of the 2025 SohIA summit with @ldaudet.bsky.social on agents and generative models !
November 27, 2024 at 9:15 AM
Opening of the 2025 SohIA summit with @ldaudet.bsky.social on agents and generative models !
Reposted by Pierre-Alexandre Mattei
Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.
November 25, 2024 at 9:55 PM
Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.