SI-NP applies self-normalized importance sampling within an EM surrogate objective, yielding consistent log-likelihood gains over NP, CNP, and ML-NP on regression and image completion benchmarks.
Uncertainty in Neural Processes
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We explore the effects of architecture and training objective choice on amortized posterior predictive inference in probabilistic conditional generative models. We aim this work to be a counterpoint to a recent trend in the literature that stresses achieving good samples when the amount of conditioning data is large. We instead focus our attention on the case where the amount of conditioning data is small. We highlight specific architecture and objective choices that we find lead to qualitative and quantitative improvement to posterior inference in this low data regime. Specifically we explore the effects of choices of pooling operator and variational family on posterior quality in neural processes. Superior posterior predictive samples drawn from our novel neural process architectures are demonstrated via image completion/in-painting experiments.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bridge the Inference Gaps of Neural Processes via Expectation Maximization
SI-NP applies self-normalized importance sampling within an EM surrogate objective, yielding consistent log-likelihood gains over NP, CNP, and ML-NP on regression and image completion benchmarks.