Research map / Probabilistic and scientific modeling / Variational and generative sampling
Path-dependent Discrete Amortized Inference
Tiago Silva, Esmeralda S. Whitammer, Salem Lahlou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Set generation (S=64, K=16) | FCS: 0.091 -> 0.053 | Improved |
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Set generation (S=64, K=24) | FCS: 0.105 -> 0.064 | Improved |
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Sequence design (Syn-8) | FCS: 0.084 -> 0.011 | Improved |
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Sequence design (Syn-32) | FCS: 0.243 -> 0.055 | Improved |
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Sequence design (SIX6) | FCS: 0.165 -> 0.135 | Improved |
| use path-dependent latent state instead of Markovian policy | GFlowNet sampler · Sequence design (PHO4) | FCS: 0.175 -> 0.130 | Improved |
Closest papers by meaning
- Improved off-policy training of diffusion samplers (NeurIPS 2024 · similarity 0.87)
- Hierarchical Variational Policies for Reward-Guided Diffusion (NeurIPS 2026 · similarity 0.86)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.86)
- Split Gibbs Discrete Diffusion Posterior Sampling (NeurIPS 2025 · similarity 0.85)
- MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control (NeurIPS 2025 · similarity 0.85)
- Delta-AI: Local objectives for amortized inference in sparse graphical models (ICLR 2024 · similarity 0.85)
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.
