Michele Caprio
@mic_caprio
Followers
495
Following
65K
Media
8
Statuses
741
Lecturer (Asst. Prof.) @csmcr. On this profile, math (Imprecise Probabilities/Stats/AI/ML), baseball (@Phillies), and football (@juventusfcen).
Manchester, England
Joined February 2012
Join us! โ Come work with Wei Pan, Richard Allmendinger, and me on Uncertainty-Aware Robotics :)
findaphd.com
PhD Project - [FSE Bicentenary PhD] Conformal World Models: A Framework for Trustworthy Human-AI Interaction in Robotics at The University of Manchester, listed on FindAPhD.com
1
0
6
Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequality
arxiv.org
We present a new framework for analysing the Expectation Maximization (EM) algorithm. Drawing on recent advances in the theory of gradient flows over Euclidean-Wasserstein spaces, we extend...
0
6
33
Our next SIPTA seminar is only a few days away! Join us on November 26 at 15:00 CET to hear from Kevin Blackwell about how to deal with the awareness problem with sets of desirable gambles. All the info at https://t.co/HUHhRTuCxc
0
2
5
๐น Job alert: Postdocs/research fellows in probabilistic machine learning at ELLIS Institute Finland & Manchester Centre for AI Fundamentals ๐ Helsinki ๐ซ๐ฎ & Manchester ๐ด๓ ง๓ ข๓ ฅ๓ ฎ๓ ง๓ ฟ ๐
Apply by Dec 1st ๐
0
2
8
Peter Scholze: Six-Functor Formalisms https://t.co/rT5YETK8sH
https://t.co/Pbwz1VplmA
arxiv.org
These are lecture notes for a course in Winter 2022/23, updated and completed in October 2025. The goal of the lectures is to present some recent developments around six-functor formalisms, in...
0
20
117
We at TMLR are proud to announce that selected papers will now be eligible for an opportunity to present at the joint NeurIPS/ICML/ICLR Journal-to-Conference (J2C) Track: https://t.co/CyjZtqbnBS
medium.com
Great news! Weโre excited to announce that selected papers published in the Transactions on Machine Learning Research (TMLR) will now beโฆ
14
78
460
Interested in my new course? Imprecise Probabilistic Machine Learning (IPML) ๐ https://t.co/FNtKqBRaJa Then, register here: https://t.co/RpDPaXqAMS It began on Oct 17, 2025, and takes place every Friday from 10:15 AM to 11:45 PM (CET).
cispa-de.zoom.us
Welcome! You are invited to join a meeting: Lecture: Imprecise Probabilistic Machine Learning (IPML). After registering, you will receive a confirmation email about joining the meeting.
12
50
289
Looking back on a phenomenal workshop in Ascona -- what a fantastic experience! Every talk was captivating. And Zurich afterwards made its mark as one of my favourite European cities. Thanks again @FannyYangETH Niao He Santiago Mazuelas for organizing such a memorable workshop!
0
2
34
A distilled version of my paper on how Category Theory can help us study the *cardinal* Uncertainty Quantification capabilities of AI methods, and in particular Conformal Prediction, is now published in the SIPTA blog! Let me know what you think :)
1
0
3
An improved version of my joint work with @sabinasloman and @samikaski on Statistical Learning Theory in the presence of severe Epistemic Uncertainty is on the ArXiV now! Let un know what you think :)
In the presence of noisy data, the learner faces epistemic uncertainty (EU) at test time which, in many cases, cannot be resolved on the basis of training data alone. What to do then? @sabinasloman, @samikaski and I tried to answer this in https://t.co/hWSeTmKcAD 1/3
0
3
13
Computer scientists, economists, and statisticians all love Blackwell's theorem --- they just disagree about what theorem they are talking about! Hard to think of anyone beyond Von Neumann who had this kind of impact on so many diverse fields.
A pleasure to be invited by Lisa Blackwell, granddaughter of Prof. David Blackwell, to say a few words about her grandfather at an event this afternoon to promote an upcoming documentary about his life. To quote my colleague Mike Jordan, Blackwell's 'approachability' theory is
5
20
186
Missed it? The video of the SIPTA seminar of Michele Caprio is now available on our youtube channel! Check it out at https://t.co/ICsp0CYj0E
0
2
6
Join us today at 15:00 CET in our first SIPTA seminar of the season! Michele Caprio will tell us about the connections between conformal prediction and imprecise probabilities. All the info and the zoom link at https://t.co/HUHhRTuCxc
0
2
4
The new season of the SIPTA seminars is already here, and we are excited to start on October 1 with Michele Caprio, who will tell us about the connections between conformal prediction and imprecise probabilities. All the info at https://t.co/HUHhRTvamK
0
2
8
Happy to share that our paper on Integral Imprecise Probability Metrics has been accepted at @NeurIPSConf 2025. We'll present it at @EurIPSConf 2025; see you in Copenhagen!
๐ง How do we compare uncertainties that are themselves imprecisely specified? ๐กMeet IIPM (Integral IMPRECISE probability metrics) and MMI (Maximum Mean IMPRECISION): frameworks to compare and quantify Epistemic Uncertainty! With the amazing @mic_caprio and @krikamol ๐
2
0
15
๐ Submission details: - Non-archival papers (4โ6 pages, excl. refs/appendices) - Deadline: Oct 17, 2025 We welcome both theoretical work & applications on reasoning and decision-making under epistemic uncertainty.
1
1
2
๐ข Call for Papers โ EIML@EurIPS2025 ๐ The 1st Workshop on Epistemic Intelligence in Machine Learning will be held at EurIPS 2025, Copenhagen this December !! ๐ https://t.co/ObOhmeTsmK
1
6
14
I'll be presenting my recent paper on Categorical Conformal Prediction ( https://t.co/7BLz9WbyTM) at @MIT's Zardini Lab ( https://t.co/4g9eyRyx5Y) on September 15, 1 pm EST. ๐๏ธ I'm beyond grateful to @GioeleZardini for the invite! Join us on Zoom:
0
0
4