Functional Distribution Networks (FDN)
Modern probabilistic regressors often remain overconfident under distribution shift. Functional Distribution Networks (FDN) place input-conditioned distributions over network weights, producing predictive mixtures whose dispersion adapts to the input; we train them with a Monte Carlo beta-ELBO objective. We pair FDN with an evaluation protocol that separates interpolation from extrapolation and emphasizes simple OOD sanity checks. On controlled 1D tasks and small/medium UCI-style regression benchmarks, FDN remains competitive in accuracy with strong Bayesian, ensemble, dropout, and hypernetwork baselines, while providing strongly input-dependent, shift-aware uncertainty and competitive calibration under matched parameter and update budgets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Nowcasting distributions: a functional MIDAS model
We propose a functional MIDAS model to leverage high-frequency information for forecasting and nowcasting distributions observed at a lower frequency. We approximate the low-frequency distribution using Functional Princi…
modelLocal moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance
We present \emph{Local Moment Matching (LMM)}, a unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance. We construct an efficiently computable estimator that achie…
Cluster weighted models with multivariate skewed distributions for functional data
We propose a clustering method, funWeightClustSkew, based on mixtures of functional linear regression models and three skewed multivariate distributions: the variance-gamma distribution, the skew-t distribution, and the …
ClusteringLearning Functional Distributional Semantics with Visual Data
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a n…
Language AcquisitionLearning Functional Distributional Semantics with Visual Data
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a n…
Language Acquisition