134 citations · 306 across the 23 of their papers we have counts for
6 papers · 1 filter
Assessing high-order effects in feature importance via predictability decomposition
Marlis Ontivero-Ortega, Luca Faes, Jesus M Cortes +2
Leveraging the large body of work devoted in recent years to describe redundancy and synergy in multivariate interactions among random variables, we propose a novel approach to qua…
Network Representation of Higher-Order Interactions Based on Information Dynamics
Gorana Mijatovic, Yuri Antonacci, Michal Javorka +3
Many complex systems in science and engineering are modeled as networks whose nodes and links depict the temporal evolution of each system unit and the dynamic interaction between…
Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition
Kenzo Clauw, Sebastiano Stramaglia, Daniele Marinazzo
This paper studies emergent phenomena in neural networks by focusing on grokking where models suddenly generalize after delayed memorization. To understand this phase transition, w…
Large language models surpass human experts in predicting neuroscience results
Xiaoliang Luo, Akilles Rechardt, Guangzhi Sun +36
Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offe…
Disentangling high order effects in the transfer entropy
Sebastiano Stramaglia, Luca Faes, Jesus M. Cortes +1
Transfer Entropy (TE), the primary method for determining directed information flow within a network system, can exhibit bias - either in deficiency or excess - during both pairwis…
Assessing High-Order Links in Cardiovascular and Respiratory Networks via Static and Dynamic Information Measures
Gorana Mijatovic, Laura Sparacino, Yuri Antonacci +4
The network representation is becoming increasingly popular for the description of cardiovascular interactions based on the analysis of multiple simultaneously collected variables.…