Research map / Probabilistic and scientific modeling / Variational and generative sampling

Inter-domain Inference for Gaussian Process Variational Autoencoders

NeurIPS 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a scalable inference framework for GPVAEs that uses inter-domain inducing variables, as the abstract indicates, to address the computational cost of GP latent priors.

Problem

GPVAE inference is computationally prohibitive at scale; existing inducing-point methods are restricted to evaluations in the input domain and offer limited control over inductive bias.

Approach

Uses inducing variables defined in a domain other than the input domain (inter-domain inference) for GP latent priors in GPVAEs, giving more control over inductive bias than standard inducing points. Details beyond the abstract are unavailable.

Experimental setup

Builds on: GPVAE inducing points

Closest papers by meaning

• Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling (ICML 2025 · similarity 0.92)
• Gaussian Process Prior Variational Autoencoders (NeurIPS 2018 · similarity 0.92)
• Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders (CVPR 2022 · similarity 0.90)
• Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models (ICML 2025 · similarity 0.90)
• Variational Inference for Gaussian Process Models with Linear Complexity (NeurIPS 2017 · similarity 0.89)
• Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference (ICML 2024 · similarity 0.87)