Lorenzo Loconte
@loreloc.bsky.social
#probabilistic-ml #circuits #tensor-networks
PhD student @ University of Edinburgh
https://loreloc.github.io/
PhD student @ University of Edinburgh
https://loreloc.github.io/
Reposted by Lorenzo Loconte
We're glad to announce the NeSy 2025 Test of Time award for "Probabilistic Inference Modulo Theories"!
🏆Rodrigo de Salvo Braz was here to accept the award.
This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
🏆Rodrigo de Salvo Braz was here to accept the award.
This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
September 9, 2025 at 9:11 PM
We're glad to announce the NeSy 2025 Test of Time award for "Probabilistic Inference Modulo Theories"!
🏆Rodrigo de Salvo Braz was here to accept the award.
This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
🏆Rodrigo de Salvo Braz was here to accept the award.
This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
You can find the speakers bios and the abstracts of presentations here: april-tools.github.io/colorai/spea...
Check them out!
Check them out!
speakers | colorai
The AAAI Workshop on Connecting Low-Rank Representations in AI
april-tools.github.io
March 4, 2025 at 8:50 PM
You can find the speakers bios and the abstracts of presentations here: april-tools.github.io/colorai/spea...
Check them out!
Check them out!
The last speaker of the workshop is Alexandros Georgiou, who is giving an introduction to polynomial networks and equivariant tensor network architecture, as well as how to implement them.
March 4, 2025 at 8:45 PM
The last speaker of the workshop is Alexandros Georgiou, who is giving an introduction to polynomial networks and equivariant tensor network architecture, as well as how to implement them.
After lunch break, Andrew G. Wilson (@andrewgwils.bsky.social) is now giving his presentation on the importance of linear algebra structures in ML, as well as on how to navigate such structures in practice.
March 4, 2025 at 7:36 PM
After lunch break, Andrew G. Wilson (@andrewgwils.bsky.social) is now giving his presentation on the importance of linear algebra structures in ML, as well as on how to navigate such structures in practice.
After Nadav it is now the turn of Guillaume Rabusseau, who is joining us online
Guillaume guides us through interesting expressiveness relationships of families of RNNs that are parameterized through tensor factorizations techniques
Guillaume guides us through interesting expressiveness relationships of families of RNNs that are parameterized through tensor factorizations techniques
March 4, 2025 at 5:05 PM
After Nadav it is now the turn of Guillaume Rabusseau, who is joining us online
Guillaume guides us through interesting expressiveness relationships of families of RNNs that are parameterized through tensor factorizations techniques
Guillaume guides us through interesting expressiveness relationships of families of RNNs that are parameterized through tensor factorizations techniques
Reposted by Lorenzo Loconte
Right, but what are Causal NFs again? In case you missed our NeurIPS 2023 Oral, Causal NFs are Deep Learning models that learn causal systems (SCMs) while having *theoretical guarantees*!
In short, you can accurately use them for causal inference tasks 🧪
arxiv.org/abs/2306.05415
In short, you can accurately use them for causal inference tasks 🧪
arxiv.org/abs/2306.05415
Causal normalizing flows: from theory to practice
In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observat...
arxiv.org
February 13, 2025 at 5:54 PM
Right, but what are Causal NFs again? In case you missed our NeurIPS 2023 Oral, Causal NFs are Deep Learning models that learn causal systems (SCMs) while having *theoretical guarantees*!
In short, you can accurately use them for causal inference tasks 🧪
arxiv.org/abs/2306.05415
In short, you can accurately use them for causal inference tasks 🧪
arxiv.org/abs/2306.05415