Trending
Emmanuel Esposito's Avatar

Emmanuel Esposito

@emmanuelesposito

Postdoc at the University of Milan, member of the LAILA Lab https://emmanuelesposito.it

50
Followers
106
Following
1
Posts
18.11.2024
Joined
Posts Following

Latest posts by Emmanuel Esposito @emmanuelesposito

Post image

๐Ÿ“ฃ Reinforcement Learning Summer School is returning to Milan in 2026!

Co-organized with @ellisunitmilan.bsky.social & designed for Master's and PhD students on RL theory, multi-agent systems, RL & LLMs, real-world applications...

๐Ÿ“ Milan ๐Ÿ‡ฎ๐Ÿ‡น
๐Ÿ“… 3-12 June
โฐ Apply by 27 March
๐Ÿ”— https://bit.ly/4b2Plhp

04.03.2026 14:49 ๐Ÿ‘ 21 ๐Ÿ” 10 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
The Central Challenge in Explainable AI: Channel Capacity Explainable AI is about communication: we want to tell people how or whya machine learning model is making certain decisions. Why is this sodifficult? In this post I take an information-theoretic pers...

When reading a large literature, it is really helpful to have opinionated opinions that help to categorize papers.

One of mine for explainable AI is that methods need to address a fundamental limit in how much information can be communicated.

Blog post: www.timvanerven.nl/blog/xai-com... (no math)

21.11.2025 13:11 ๐Ÿ‘ 8 ๐Ÿ” 4 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
Theory of XAI Workshop Explainable AI (XAI) is now deployed across a wide range of settings, including high-stakes domains in which misleading explanations can cause real harm. For example, explanations are required by law ...

The schedule for our Workshop on the Theory of XAI is now online!

๐Ÿ•ฐ๏ธ Dec 2, starting 9am
๐Ÿ“ Bella Center Copenhagen (co-located with EurIPS)
๐Ÿ”— sites.google.com/view/theory-...

12.11.2025 10:45 ๐Ÿ‘ 3 ๐Ÿ” 2 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

How can we make AI explanations provably correct โ€” not just convincing? ๐Ÿค”

Join us for the Theory of Explainable Machine Learning Workshop, part of the ELLIS UnConference Copenhagen ๐Ÿ‡ฉ๐Ÿ‡ฐ on Dec 2, co-located with #EurIPS.

๐Ÿ•’ Call for contributions open until Oct 15 (AoE)
๐Ÿ”— eurips.cc/ellis

13.10.2025 09:10 ๐Ÿ‘ 13 ๐Ÿ” 4 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Preview
Theory of XAI Workshop Explainable AI (XAI) is now deployed across a wide range of settings, including high-stakes domains in which misleading explanations can cause real harm. For example, explanations are required by law ...

Interested in provable guarantees and fundamental limitations of XAI? Join us at the "Theory of Explainable AI" workshop Dec 2 in Copenhagen! @ellis.eu @euripsconf.bsky.social

Speakers: @jessicahullman.bsky.social @doloresromerom.bsky.social @tpimentel.bsky.social

Call for Contributions: Oct 15

07.10.2025 12:53 ๐Ÿ‘ 8 ๐Ÿ” 5 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 2

Registrations for EurIPS in Copenhagen are open !
Iโ€™ll be there, the whole week, and Iโ€™m truly looking forward to this local parallel event.

02.10.2025 22:01 ๐Ÿ‘ 21 ๐Ÿ” 2 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Preview
Theory of XAI Workshop Explainable AI (XAI) is now deployed across a wide range of settings, including high-stakes domains in which misleading explanations can cause real harm. For example, explanations are required by law ...

And Theory results for Explainable Machine Learning!

Call for extended abstracts open until October 15, AoE.

sites.google.com/view/theory-...

03.10.2025 10:53 ๐Ÿ‘ 3 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Time to figure out which provable guarantees one can(not) give on XAI! Workshop "Theory of Explainable Machine
Learning", Dec 2 in Copenhagen as part of the Ellis
Unconference/EurIPS. Submission deadline: Oct 15.

sites.google.com/view/theory-...
eurips.cc/ellis/

01.10.2025 03:30 ๐Ÿ‘ 8 ๐Ÿ” 3 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
Theory of XAI Workshop, Dec 2, 2025 Explainable AI (XAI) is now deployed across a wide range of settings, including high-stakes domains in which misleading explanations can cause real harm. For example, explanations are required by law ...

๐Ÿšจ Workshop on the Theory of Explainable Machine Learning

Call for โ‰ค2 page extended abstract submissions by October 15 now open!

๐Ÿ“ Ellis UnConference in Copenhagen
๐Ÿ“… Dec. 2
๐Ÿ”— More info: sites.google.com/view/theory-...

@gunnark.bsky.social @ulrikeluxburg.bsky.social @emmanuelesposito.bsky.social

30.09.2025 14:00 ๐Ÿ‘ 8 ๐Ÿ” 4 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

EurIPS is coming! ๐Ÿ“ฃ Mark your calendar for Dec. 2-7, 2025 in Copenhagen ๐Ÿ“…

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

16.07.2025 22:00 ๐Ÿ‘ 143 ๐Ÿ” 70 ๐Ÿ’ฌ 2 ๐Ÿ“Œ 19
Post image

Mark your calendars, EWRL is coming to Tรผbingen! ๐Ÿ“…
When? September 17-19, 2025.
More news to come soon, stay tuned!

08.04.2025 08:33 ๐Ÿ‘ 38 ๐Ÿ” 14 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 5
Preview
NeurIPS participation in Europe We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Sรธren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

30.03.2025 18:04 ๐Ÿ‘ 280 ๐Ÿ” 160 ๐Ÿ’ฌ 6 ๐Ÿ“Œ 12
Bandit Theory Symposium Tim van Ervenโ€™s website

With Jack Mayo we are organizing a symposium on theory of bandit algorithms on March 10 at the University of Amsterdam.

Talks by Jack Mayo, Wouter Koolen, Julia Olkhovskaya, Dirk van der Hoeven and, tentatively, Tor Lattimore.

www.timvanerven.nl/events/bandi... has details and (free) registration

20.02.2025 10:31 ๐Ÿ‘ 12 ๐Ÿ” 3 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

The theory of interpretable AI seminar is back after the holiday season! ๐ŸŽ…๐Ÿคถ

Our next talk is next Thursday by Yishay Mansour who will talk about interpretable approximations

๐Ÿ’ป Website: tverven.github.io/tiai-seminar/
โฐDate: 16 Jan

10.01.2025 08:05 ๐Ÿ‘ 10 ๐Ÿ” 3 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 1

As we start the new year, I would like to remind everyone that it is now almost 120 years since the US decided consumer protection - by which I mean regulation - mattered. Given the upcoming presidential inauguration, let's talk about how that happened - and why it's so important. (A thread)

06.01.2025 20:42 ๐Ÿ‘ 1167 ๐Ÿ” 478 ๐Ÿ’ฌ 38 ๐Ÿ“Œ 69

I'll be in Vancouver for #NeurIPS2024! Feel free to text me if you want to meet and chat

09.12.2024 00:37 ๐Ÿ‘ 3 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0