Research map / Learning theory and algorithms / Sample complexity
Optimal randomized multilevel Monte Carlo for repeatedly nested expectations
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 recursive randomized multilevel Monte Carlo (READ) instead of NMC1 | Nested expectation estimation · Toy nested expectation, D=2 | empirical MSE convergence slope: -0.35 -> -0.97 | Helped |
| Use recursive randomized multilevel Monte Carlo (READ) instead of NMC2 | Nested expectation estimation · Toy nested expectation, D=2 | empirical MSE convergence slope: -0.47 -> -0.97 | Helped |
| Use READ instead of NMC1 | Bermudan basket put pricing · Bermudan basket put, D=3 | computational cost: 2.05\times 10^{11} -> 6.9\times 10^7 | Helped |
| Use READ instead of NMC2 | Bermudan basket put pricing · Bermudan basket put, D=3 | computational cost: 1.22\times 10^{11} -> 6.9\times 10^7 | Helped |
| Use READ instead of NMC1 | Bermudan basket put pricing · Bermudan basket put, D=4 | computational cost: 4.88\times 10^{10} -> 2.36\times 10^8 | Helped |
| Use READ instead of NMC2 | Bermudan basket put pricing · Bermudan basket put, D=4 | computational cost: 5.69\times 10^{10} -> 2.36\times 10^8 | Helped |
| Replace READ with NMC1 | Bermudan basket put pricing · Bermudan basket put, D=3 | estimate: 2.159 (0.008) -> 2.169 (0.005) | Mixed |
| Replace READ with NMC2 | Bermudan basket put pricing · Bermudan basket put, D=4 | estimate: 2.284 (0.065) -> 2.393 (0.003) | Mixed |
Closest papers by meaning
- Nested Expectations with Kernel Quadrature (ICML 2025 · similarity 0.89)
- Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need (ICML 2024 · similarity 0.87)
- Variance Reduction for Expectations with Diffusion Teachers (NeurIPS 2026 · similarity 0.82)
- Quantum speedup of non-linear Monte Carlo problems (NeurIPS 2025 · similarity 0.82)
- Fearless Stochasticity in Expectation Propagation (NeurIPS 2024 · similarity 0.82)
- Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport (ICML 2025 · similarity 0.81)
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.