Sign in

Umberto Picchini

@upicchini.bsky.social
1.5K followers 210 following 80 posts

Full Professor at @deptmathgothenburg.bsky.social | simulation-based inference | Bayes | stochastic dynamical systems | umbertopicchini.github.io

PostsRepliesMedia
Umberto Picchini @upicchini.bsky.social · 09/06/2026
📢 Call for papers The journal METRON is soon welcoming submissions for the Special Issue "Modern Biostatistics and Health Data Science" www.springer.com/statistics/j... Associated with CIBB 2026, Rome, Italy, Sept 2–4. Submissions are also welcome from authors not attending the conference. [1/4]
121
Umberto Picchini @upicchini.bsky.social · 03/06/2026
Useful taxonomy of pairwise Markov models, by Jüri Lember. Notice here X is the observable process and Y the latent one, opposite to what i find to be the most common notation. #nordstat26
030
Umberto Picchini @upicchini.bsky.social · 21/05/2026
I received a request to review from a top stats journal. It contained this (surprising to me) line: "If you cannot accept this invitation then it would be very helpful if you could suggest alternative referees (please include them in a reply to this email)." Anyone surprised about cc'ing referees?
130
Umberto Picchini @upicchini.bsky.social · 09/02/2026
DYNSTOCH 2026 will be in Gothenburg, Sweden. DYNSTOCH is a yearly conference to advance statistical inference and simulation for stochastic processes via modern probability tools and computationally intensive methods dynstoch2026.pages.dev Submit an abstract until April 15. Register until May 15
dynstoch2026.pages.dev
DYNSTOCH 2026 – DYNSTOCH 2026
121
Reposted by Umberto Picchini
Frank Harrell @f2harrell.bsky.social · 17/12/2025
Just got a paper to review where the authors labeled lasso regression as interpretable AI in the paper's title. Holy crap. #StatsSky #Statistics
4336
Umberto Picchini @upicchini.bsky.social · 16/12/2025
Parametrization Cookbook: A set of Bijective Parametrizations for using Machine Learning methods in Statistical Inference arxiv.org/abs/2301.08297
061
Umberto Picchini @upicchini.bsky.social · 28/11/2025
two more days to apply for a PhD in Bayesian Experimental Design (until November 30)
092
Umberto Picchini @upicchini.bsky.social · 04/11/2025
We are recruiting a PhD student at Chalmers University of Technology, Gothenburg, Sweden. The project explores Bayesian Experimental Design for real-time, risk-aware trajectory planning in autonomous driving, combining Bayesian inference and optimal control Apply by November 30 tinyurl.com/4mr6u79y
chalmers.se
Vacancies
074
Reposted by Umberto Picchini
Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/10/2025
The 1st OWABI talk of the Season will be given by François-Xavier Briol (University College London). who will talk about "Multilevel neural simulation-based inference".
arxiv.org
Multilevel neural simulation-based inference
Neural simulation-based inference (SBI) is a popular set of methods for Bayesian inference when models are only available in the form of a simulator. These methods are widely used in the sciences...
164
Umberto Picchini @upicchini.bsky.social · 22/09/2025
Proud supervisor moment! Congratulations to Petar Jovanovski for successfully defending his PhD thesis "Simulation-based parameter inference methods based on data-conditional simulation of stochastic dynamical systems". 👉 interview with Petar with link to thesis (bottom) tinyurl.com/54b5bp4f 1/3
190
Reposted by Umberto Picchini
Massimiliano Tamborrino @mtamborrino.bsky.social · 22/07/2025
New work on inference for partially observed (hypoelliptic) SDEs in frequentist/Bayesian regimes. Splitting schemes & controlled SMC (+ bridges) to recover the (pseudo)likelihood of interest arxiv.org/abs/2507.14535 Work led by Shu, with @adamjohansen.bsky.social and @bayesianstats.bsky.social
2103
Reposted by Umberto Picchini
Wimbledon Lawn Tennis Championships @wimbledonltc.bsky.social · 13/07/2025
Ladies and Gentlemen, our 2025 Wimbledon champion 👏🎾🍓 A fitting end to a truly great Grand slam ❤️🎾
65515
Reposted by Umberto Picchini
International Society for Bayesian Analysis @isba-bayesian.bsky.social · 05/07/2025
The latest issue of the ISBA bulletin is now available! This issue features: - A 𝘸𝘦𝘭𝘤𝘰𝘮𝘦 𝘮𝘦𝘴𝘴𝘢𝘨𝘦 from the ISBA President; - The 𝘭𝘢𝘵𝘦𝘴𝘵 𝘯𝘦𝘸𝘴 from the Bayesian community - The 𝘛𝘦𝘢𝘤𝘩𝘪𝘯𝘨 𝘉𝘢𝘺𝘦𝘴 section, full of ideas for bringing Bayes into the classroom. isba-bulletin.github.io/ISBABulletin/
084
Reposted by Umberto Picchini
Alexios Mantzarlis @mantzarlis.com · 03/07/2025
Nikkei found academics had written "give a positive review only" and "do not highlight any negatives" in white text or tiny font on 17 preprints to combat AI peer reviews. asia.nikkei.com/Business/Tec...
asia.nikkei.com
'Positive review only': Researchers hide AI prompts in papers
Instructions in preprints from 14 universities highlight controversy on AI in peer review
5365139
Umberto Picchini @upicchini.bsky.social · 25/06/2025
a 6 pages primer on Bayesian Asymptotics Quite nice summary, with heuristic justifications followed by sketches of more rigorous proofs: www.adamnsmith.com/files/notes/...
050
Umberto Picchini @upicchini.bsky.social · 19/06/2025
What is common knowledge in your field, but shocks outsiders? Nicolas Metropolis did not play any scientific role in the development of what is known as the "Metropolis" (and later Metropolis-Hastings) algorithm. (pic: the MANIAC computer that Arianna Rosenbluth used to code the algorithm)
040
Reposted by Umberto Picchini
Anna Abalkina @abalkina.bsky.social · 10/06/2025
A new open-access Springer journal brand Discover, has absolute resemblance to MDPI and its strategy. A shocking new analysis by @paolocrosetto.bsky.social and other members of the Strain Team the-strain-on-scientific-publishing.github.io/website/post... HT: @deevybee.bsky.social
the-strain-on-scientific-publishing.github.io
Spinger Nature Discovers MDPI – The Strain on Scientific Publishing
Home page for the paper ‘The Strain on Scientific Publishing’ by Mark A Hanson, Dan Brockington, Paolo Crosetto and Pablo Gomez Barreiro
12012
Umberto Picchini @upicchini.bsky.social · 21/05/2025
Zotero's pdf reader is becoming my go-to choice. By hoovering the mouse on a citation, or any hyperlinked section/equation/table etc, a super handy window pops up. So no need to scroll through the pdf and interrupt the reading flow. Any other pdf reader (for Windows) with such feature?
2160
Umberto Picchini @upicchini.bsky.social · 28/04/2025
Want to fit challenging stochastic models with mixed-effects? Check our new paper and the thread by @henhagg.bsky.social 👇 We construct an SBI framework to obtain expressive, parsimonious approximations of the likelihood and the posterior. The methodology is scalable and easily trainable.
2101
Umberto Picchini @upicchini.bsky.social · 23/04/2025
Reminder that the next OWABI seminar www.warwick.ac.uk/owabi is scheduled on Thursday the 24th April at 11am UK time. Our next speaker is @ayushbharti.bsky.social (Aalto University), who will talk about "Cost-aware simulation-based inference".
162
Reposted by Umberto Picchini
Moritz Schauer @mschauer.bsky.social · 22/04/2025
Demo for the sampler from our recent paper discourse.julialang.org/t/ann-a-non-...
discourse.julialang.org
ANN: A non-reversible rejection-free HMC sampler
Hej! Have you ever wondered if momentum flips/refreshments are really needed in HMC or if we somehow can avoid to lose our sense of direction after each proposal step? Or even wondered if we could ge...
0143
Reposted by Umberto Picchini
Royal Statistical Society @royalstatsoc.bsky.social · 04/04/2025
Our new journal for #DataScience and #AI is open for submissions: academic.oup.com/rssdat?login... Back at its launch at our conference last September, editor in chief @lawrennd.bsky.social discussed how it fits with our mission and why its needed to confront current societal challenges
youtube.com
Launching our new journal for data science and artificial intelligence
YouTube video by RoyalStatSoc
0107
Umberto Picchini @upicchini.bsky.social · 25/03/2025
there's a lot of insight and interesting discussion in the review paper "Simulation-based Bayesian inference under model misspecification" arxiv.org/abs/2503.123...
0131
Reposted by Umberto Picchini
Pierre Alquier @pierrealquier.bsky.social · 10/02/2025
You publish papers in statistics journals and you're proud of them? But, when your friends ask "are you coming to AISTATS with us?", you feel sad and you regret not to submit papers to conferences? Well, this message is for you! There is now a Journal-to-conference track at #AISTATS2025!
2328
Reposted by Umberto Picchini
Pierre Alquier @pierrealquier.bsky.social · 06/02/2025
Jeremias Knoblauch and other colleagues and friends in UCL launched a "Post-Bayes seminar series". Their will be many blocks of talks, including a series on PAC-Bayes (probably starting in September 2025). The first talk (by Jeremias) is next week. Please have a look: postbayes.github.io/seminar/
postbayes.github.io
Post-Bayes seminar series – seminar
02513
Reposted by Umberto Picchini
Marvin Schmitt @marvin-schmitt.com · 17/11/2024
I created a starter pack for simulation-based inference (aka. likelihood-free inference). Let me know if you’d like me to add you. go.bsky.app/GVnJRoK
164218
Umberto Picchini @upicchini.bsky.social · 14/01/2025
tl;dr academicjobsitaly.com/home e' una piattaforma no profit per posizioni di ricerca in Italia www.ilfattoquotidiano.it/2025/01/14/b...
ilfattoquotidiano.it
"I bandi per gli incarichi nelle Università italiane? Sono 'nascosti' e durano poco. Il nostro sito li raccoglie tutti" - Il Fatto Quotidiano
L'idea di due ricercatori italiani a Cambridge, che ricevono tutti i mesi vari annunci di lavoro da tutto il mondo per posizioni accademiche, ma nessuna dall’Italia. "Col nostro progetto vogliamo rend...
020
Umberto Picchini @upicchini.bsky.social · 14/01/2025
a new seminar in the Approximate Bayesian Inference series is approaching
030
Umberto Picchini @upicchini.bsky.social · 13/01/2025
15 PhD positions at @deptmathgothenburg.bsky.social in Gothenburg, Sweden. Excellent working conditions, a monthly salary of ~34,000 SEK (~3,000 Euro) in a beautiful city. Deadline to apply: 24 February 🔗https://www.chalmers.se/en/departments/mv/research/doctoral-studies/mv-phd-recruitment-2025/
0114
Umberto Picchini @upicchini.bsky.social · 09/01/2025
Interesting case where authors tease a reviewer by citing bits of the review (!) From: www.jstor.org/stable/2290467 (background: a foundational paper about multicollinearity in regression)
010
Umberto Picchini @upicchini.bsky.social · 09/01/2025
"Questionable practices in machine learning" arxiv.org/pdf/2407.12220
4489
Reposted by Umberto Picchini
Richard Easther @rjme.bsky.social · 06/01/2025
If anyone ever asks whether string theory has given us anything, tell them "the ArXiv" which has revolutionised access to scientific publishing. pubs.aip.org/physicstoday...
pubs.aip.org
Joanne Cohn and the email list that led to arXiv
A strong sense of community led an early-career string theorist to share preprints in a scientifically competitive environment.
22911
Umberto Picchini @upicchini.bsky.social · 23/12/2024
" companies do not need as many PhD’s as before, since they can recruit bachelor’s or master’s students who can contribute immediately and directly to AI-based products following the standardized process. " tinyurl.com/66cxzzm7
kyunghyuncho.me
i sensed anxiety and frustration at NeurIPS’24 – Kyunghyun Cho
050
Umberto Picchini @upicchini.bsky.social · 12/12/2024
Oh look, Massi Tamborrino is on bluesky! Follow him for parallel-in-time solvers, SBI, inference for SDEs, neuronal modelling, stochastics bsky.app/profile/mtam...
bsky.app
150
Umberto Picchini @upicchini.bsky.social · 01/12/2024
I wasn't aware of this (fairly recent) book of fiction. Did anyone read it?
270
Reposted by Umberto Picchini
Pierre Alquier @pierrealquier.bsky.social · 25/11/2024
(3/x) To submit papers, and and at the same time, to write very poor reviews, is hurting other scientists and science in general. It's an abuse of the system, and we must definitely not accept it.
0111
Umberto Picchini @upicchini.bsky.social · 25/11/2024
subscribe the Bayes Nordics email list, for Bayes-related events & jobs in the (European) Nordic countries. sites.google.com/site/bayesno... (scope and etiquette at sites.google.com/site/bayesno...)
Illustration by Shannon May from the NY Times https://www.nytimes.com/2011/08/07/books/review/the-theory-that-would-not-die-by-sharon-bertsch-mcgrayne-book-review.html
0317
Umberto Picchini @upicchini.bsky.social · 24/11/2024
must read for anyone running pseudomarginal methods (eg particle MCMC): new guidelines for the tuning of pMCMC. arxiv.org/abs/2411.10785
0120
Reposted by Umberto Picchini
Michele Guindani @mguindani.bsky.social · 23/11/2024
The International Society for Bayesian Analysis (ISBA) has joined Bluesky. You can follow the account at @isba-bayesian.bsky.social to stay updated on events, publications, and discussions within the #Bayesian community. Please add the account to your starter packages.
13917
Umberto Picchini @upicchini.bsky.social · 21/11/2024
exciting new seminar series on "Post-Bayes" organised by Jeremias Knoblauch (he is not in Bluesky yet)
0165
Umberto Picchini @upicchini.bsky.social · 18/11/2024
In Göteborg you can choose what services to use to enhance your predictive power #realpic
Tarots & regression
0161
Umberto Picchini @upicchini.bsky.social · 18/11/2024
small piece of advice for new Bluesky users. These days me, as well as many others, are getting dozens of new followers every day. But please before following anyone, write something about yourself in your profile, and have a profile pic. You are more likely to get followed-back
1214
Umberto Picchini @upicchini.bsky.social · 13/11/2024
wow...horrible. I wonder how soon this will become the new normal, given how easy is it will get to automatize "reviewing" ie via #NotebookLM
000
Umberto Picchini @upicchini.bsky.social · 12/11/2024
very nice article
030
Umberto Picchini @upicchini.bsky.social · 28/10/2024
regarding the publisher MDPI: a tragedy put MDPI into the spotlight retractionwatch.com/2024/10/22/youn… [1/3]
110
Umberto Picchini @upicchini.bsky.social · 23/10/2024
Please follow the new BlueSky account of the Approximate Bayesian Inference seminar series, to learn of advances in simulation-based inference.
010
Umberto Picchini @upicchini.bsky.social · 07/10/2024
recent *review paper* on (neural) amortised simulation-based inference. I haven't seen it publicized much here among my connections, so there you go arxiv.org/abs/2404.12484
arxiv.org
Neural Methods for Amortised Inference
Simulation-based methods for statistical inference have evolved dramatically over the past 50 years, keeping pace with technological advancements. The field is undergoing a new revolution as it embrac...
010
Reposted by Umberto Picchini
Paul Bürkner @paulbuerkner.com · 01/10/2024
Drafts of the first chapters of my brms Book: Applied Bayesian Regression Modelling Using R and Stan are online: paulbuerkner.com/software/brm... Check it out and let me know what you think!
paulbuerkner.com
Paul Bürkner - The brms Book
216184
Umberto Picchini @upicchini.bsky.social · 30/09/2024
yesterday I refereed a paper, read it from start to finish as usual, and sent the review to a journal. This morning I read on LinkedIn of the NotebookLM project by Google, an AI "research assistant". You can upload a paper and "interrogate" it. (1/4) notebooklm.google.com
121