Scholar
LightNews

Mirco Musolesi

Videos
H-index: 55
Computer science 51%
Physics 21%
more

by Mirco Musolesi

mircomusolesi.bsky.social
New preprint with Charles Westphal and Stephen Hailes: "A Generalized Information Bottleneck Theory of Deep Learning". In this work, we introduce the Generalized Information Bottleneck framework, a synergy-based reformulation of the Information Bottleneck theory. arxiv.org/abs/2509.26327

by Mirco Musolesi

mircomusolesi.bsky.social
Lots of headlines claim graduates are more likely to be unemployed than non-graduates. Graduate unemployment panic makes good headlines, but the data says otherwise. Great analysis by @jburnmurdoch.ft.com. www.ft.com/content/ea9e...

.
What the graduate unemployment story gets wrong
People with a degree are faring better, not worse than their non-graduate counterparts
www.ft.com
2

by Mirco Musolesi

by Mirco Musolesi

by Mirco Musolesi

mircomusolesi.bsky.social
New preprint: “Complexity-Driven Policy Optimization”. The paper discusses a novel complexity-driven policy optimisation solution for efficient and robust approximation in Reinforcement Learning. Essentially, entropy alone is not sufficient, we also need "structure".
gfranceschelli.bsky.social
gfranceschelli.bsky.social @gfranceschelli.bsky.social · 7d
📢 New Paper!

We replace the entropy bonus in PPO with a *complexity* bonus, encouraging structured and stochastic policies that are robust to different scaling factors and can work in environments with variable exploration needs.

Read more:
arxiv.org/abs/2509.20509

w/ @mircomusolesi.bsky.social
Complexity-Driven Policy Optimization
Policy gradient methods often balance exploitation and exploration via entropy maximization. However, maximizing entropy pushes the policy towards a uniform random distribution, which represents an un...
arxiv.org
2

by Mirco Musolesi

Reposted by Mirco Musolesi

gfranceschelli.bsky.social
📢 New Paper!

We replace the entropy bonus in PPO with a *complexity* bonus, encouraging structured and stochastic policies that are robust to different scaling factors and can work in environments with variable exploration needs.

Read more:
arxiv.org/abs/2509.20509

w/ @mircomusolesi.bsky.social
Complexity-Driven Policy Optimization
Policy gradient methods often balance exploitation and exploration via entropy maximization. However, maximizing entropy pushes the policy towards a uniform random distribution, which represents an un...
arxiv.org
3

by Mirco Musolesi

by Mirco Musolesi

mircomusolesi.bsky.social
Book website: libraryoflostmaps.com
The Library of Lost Maps
libraryoflostmaps.com

by Mirco Musolesi

mircomusolesi.bsky.social
Received a copy of “The Library of Lost Maps” by my colleague James Cheshire at @uclgeography.bsky.social in the internal mail. Really beautiful (and very interesting) book. Thanks a lot James!
1 1 2

by Mirco Musolesi

mircomusolesi.bsky.social
For the geeks among you: just discovered the Apple Calculator app has a "Programmer" mode, complete with binary, hex, and related operations.
3

by Mirco Musolesi

by Mirco Musolesi

by Mirco Musolesi

mircomusolesi.bsky.social
The problem is still relevant - we now have Amazon delivery vans instead to play with. 2/2

by Mirco Musolesi

mircomusolesi.bsky.social
I was thinking about this some weeks ago. The Travelling Salesman Problem (finding the shortest path through a list of cities, visiting each only once), a classic in Computer Science/Maths, is becoming something of the past without actual salesmen on the roads. 1/2
economist.com
The Economist @economist.com · 14d
In the 1980s and 1990s salesmen slogged up and down Britain’s motorways. Today that “road-warrior” lifestyle has disappeared. There are several reasons why
British men are driving less, and a culture is vanishing
Farewell to the road warriors
econ.st
1

Reposted by Mirco Musolesi

economist.com
In the 1980s and 1990s salesmen slogged up and down Britain’s motorways. Today that “road-warrior” lifestyle has disappeared. There are several reasons why
British men are driving less, and a culture is vanishing
Farewell to the road warriors
econ.st
1 2 10

by Mirco Musolesi

mircomusolesi.bsky.social
Wonders of the natural world. I inherited an office cactus from a colleague who left. In a matter of days, out of nothing the cactus has developed a very long stem (with flowers).
Cactus.
1

by Mirco Musolesi

Reposted by Mirco Musolesi

by Mirco Musolesi

by Mirco Musolesi

mircomusolesi.bsky.social
Today Charlie Westphal will present our paper "Feature Selection for Network Intrusion Detection" in the main Research Track of ACM KDD 2025 in Toronto.

Link to the paper: dl.acm.org/doi/pdf/10.1...

#KDD2025
2

by Mirco Musolesi

Reposted by Mirco Musolesi

Reposted by Mirco Musolesi

mircomusolesi.bsky.social
I am advertising two PhD projects in the area of AI&cybersecurity as part of the new EPSRC CDT in Cyber-Physical Risk at UCL. These are fully-funded PhD studentships starting in September 2025.

Information here: ucl.ac.uk/security-cri...

Closing date: 15 April 2025.
1 2 1

Reposted by Mirco Musolesi

vadarvariu.bsky.social
Our paper "Tree search in DAG space with model-based reinforcement learning for causal discovery" has just been published in Proceedings of the Royal Society A. Joint work with Steve Hailes and @mircomusolesi.bsky.social 🧵 1/
Screenshot of the paper title, authors, abstract and miscellaneous bibliographical information as it appears in the published journal PDF.
2 2 10

Reposted by Mirco Musolesi

mircomusolesi.bsky.social
Our paper "Partial Information Decomposition for Data Interpretability and Feature Selection" with Charlie Westphal and Steve Hailes will be presented at #AISTAT2025 on Sunday.

Session details: Spot 151 in Session 2 (Sun, May 4).

Link to the paper: openreview.net/attachment?i...

Reposted by Mirco Musolesi

mircomusolesi.bsky.social
Today our paper with James Rudd-Jones and María Pérez-Ortiz "Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis" will be presented at the #AAMAS2025 Conference in Detroit.

Time: 2pm ET
Room: Richard

Link to the paper: arxiv.org/abs/2504.12777

@aamasconf.bsky.social
2 5

Reposted by Mirco Musolesi

mircomusolesi.bsky.social
The second call for applications to the CDT in Cyber-Physical Risk is now open. I am offering two projects in the area of AI and cybersecurity. I would be happy to chat about this opportunity if you are interested.

www.ucl.ac.uk/security-cri...

Closing date: 15 June 2025.
1

by Mirco Musolesi

mircomusolesi.bsky.social
Dream jobs and where to find them. linkedin.com/jobs/view/42...
1

by Mirco Musolesi

References

Fields & subjects

Updated 1m