Research map / Probabilistic and scientific modeling / Variational and generative sampling
HoT-VI: Reparameterizable Variational Inference for Capturing Instance-Level High-Order Correlations
Junxi Xiao, Qinliang Su, Zexin Yuan
Read the paperCheck your idea against 137,217 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 HoT-VI, a reparameterizable variational inference method that captures instance-level high-order correlations beyond the mean-field independence assumption.
Problem
Mean-field variational inference assumes independence, which fails for correlated data instances; existing structured VI either models latent-dimension correlations (not scalable to instance-level) or only simple first-order dependencies.
Approach
Reparameterizable variational inference that models instance-level high-order correlations, extending beyond first-order dependencies while retaining scalability of mean-field VI.
Experimental setup
Builds on: mean-field variational inference
Closest papers by meaning
- TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing (NeurIPS 2024 · similarity 0.94)
- Copula-SVI: Vine-Copula Variational Inference with Stein Refining for Instance-Level Correlation Capturing (ICML 2026 · similarity 0.90)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.88)
- Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference (NeurIPS 2025 · similarity 0.88)
- Provably Scalable Black-Box Variational Inference with Structured Variational Families (ICML 2024 · similarity 0.88)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
