Research map / Probabilistic and scientific modeling / Variational and generative sampling
DiCE: The Infinitely Differentiable Monte Carlo Estimator
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DiCE rather than repeated surrogate loss differentiation for higher-order gradients | Stochastic computation graphs · Bernoulli toy example | second derivative correctness: -2 -> -4 | Helped |
| Add a baseline for variance reduction (ablation) | DiCE gradient estimation · IPD | gradient estimation accuracy | Helped |
| Use DiCE to differentiate through opponent learning steps | LOLA · IPD | joint social welfare | Helped |
| Use a batch size of 64 rather than the much larger batches required by original LOLA | LOLA-DiCE · IPD | learning stability: 64; ~4000 | Helped |
Closest papers by meaning
- A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs (ICML 2019 · similarity 0.95)
- Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning (NeurIPS 2019 · similarity 0.90)
- Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update (ICLR 2024 · similarity 0.88)
- Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization (AAAI 2024 · similarity 0.85)
- Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching (ICML 2024 · similarity 0.84)
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.