Showing 2026Show all
2 papers · 1 filter
stat.ML2026
Decomposing A Neural Learner
Zelong Bi
Neural learners for classification and regression are often criticized as black boxes. We propose a probabilistic decomposition of neural learners that accounts for heterogeneous p…
stat.ML2026
Missing Data Imputation under Manifold Hypothesis
Zelong Bi, Amuchechukwu Ibenegbu, Sarat Moka
The manifold hypothesis posits that high-dimensional data are concentrated near a low-dimensional embedded manifold. Recent advances in mixture variational autoencoders (VAEs) prov…