Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
Arkaprabha Ganguli, Emil Constantinescu
A persistent empirical observation is that trained neural networks outperform their neural tangent kernel (NTK) limit on tasks with compositional structure, yet a quantitative acco…
stat.ML2026
Uncovering Physical Drivers of Dark Matter Halo Structures with Auxiliary-Variable-Guided Generative Models
Arkaprabha Ganguli, Anirban Samaddar, Florian Kéruzoré +4
Deep generative models (DGMs) compress high-dimensional data but often entangle distinct physical factors in their latent spaces. We present an auxiliary-variable-guided framework…
stat.ML2025
Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
Arkaprabha Ganguli, Nesar Ramachandra, Julie Bessac +1
This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigat…