7 papers
SOM-VQ: Topology-Aware Tokenization for Interactive Generative Models
Alessandro Londei, Denise Lanzieri, Matteo Benati
Vector-quantized representations enable powerful discrete generative models but lack semantic structure in token space, limiting interpretable human control. We introduce SOM-VQ, a…
Inverting Self-Organizing Maps: A Unified Activation-Based Framework
Alessandro Londei, Matteo Benati, Denise Lanzieri +1
Self-Organizing Maps (SOMs) provide topology-preserving projections of high-dimensional data, yet their use as generative models remains largely unexplored. We show that the activa…
First-Extinction Law for Resampling Processes
Matteo Benati, Alessandro Londei, Denise Lanzieri +1
Extinction times in resampling processes are fundamental yet often intractable, as previous formulas scale as with the number of states present in the initial probability…
Simulation-Based Inference Benchmark for Weak Lensing Cosmology
Justine Zeghal, Denise Lanzieri, François Lanusse +5
Standard cosmological analysis, which relies on two-point statistics, fails to extract the full information of the data. This limits our ability to constrain with precision cosmolo…
Lyapunov Learning at the Onset of Chaos
Matteo Benati, Alessandro Londei, Denise Lanzieri +1
Handling regime shifts and non-stationary time series in deep learning systems presents a significant challenge. In the case of online learning, when new information is introduced,…
Optimal Neural Summarisation for Full-Field Weak Lensing Cosmological Implicit Inference
Denise Lanzieri, Justine Zeghal, T. Lucas Makinen +3
Traditionally, weak lensing cosmological surveys have been analyzed using summary statistics motivated by their analytically tractable likelihoods, or by their ability to access hi…