Research map / Probabilistic and scientific modeling / Variational and generative sampling
Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a unified large-scale evaluation framework for Monte Carlo, variational inference, and their combinations on sampling tasks, comparing methods with common performance measures.
Problem
Sampling from intractable distributions with Monte Carlo, variational inference, and hybrids lacks a unified evaluation framework; prior studies use disparate metrics and limited method comparisons across tasks.
Approach
A unified benchmark suite that evaluates many variational, Monte Carlo, and combined sampling methods under common performance measures across diverse target distributions, rather than proposing a new sampler.
Closest papers by meaning
- Interleave Variational Optimization with Monte Carlo Sampling: A Tale of Two Approximate Inference Paradigms (AAAI 2019 · similarity 0.89)
- Annealing in variational inference mitigates mode collapse: a theoretical study on Gaussian mixtures (NeurIPS 2026 · similarity 0.87)
- Transport meets Variational Inference: Controlled Monte Carlo Diffusions (ICLR 2024 · similarity 0.87)
- Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution (ICML 2024 · similarity 0.87)
- On scalable and efficient training of diffusion samplers (NeurIPS 2025 · similarity 0.86)
- Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion (NeurIPS 2024 · similarity 0.86)
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.