Sensitivity Analysis Library in Python. Contains Sobol, Morris, FAST, and other methods.
A Sobol sequence generator for Scala and Javascript
(t, m, s)-nets generator / Генератор (t, m, s)-сетей
Sobol sequence generator
Lightweight, no_std-friendly RNG library for Rust. Xoshiro256++ default; optional Mersenne Twister, PCG32/64, ChaCha20 CSPRNG, SIMD bulk-byte (NEON/AVX2), Halton/Sobol/Van der Corput quasi-random. Ziggurat normal(), 4 built-in distributions + pluggable Distribution trait. 100% test coverage.
Python package and open direction-number data for high-dimensional Sobol’ sequences, including the 50,000-dimensional tkrg-a-ap5 set for quasi-Monte Carlo simulation.
Battery life modeling pipeline: power decomposition + WLS estimation + RK4 SOC simulation for TTE prediction; includes scenario analysis, Monte Carlo uncertainty, Sobol sensitivity, and optimization (paper/fit dual mode).
Spatial Statistic with Kriging
APEXSENSUN is a package in R for performing uncertainty and sensitivity analysis for the APEX model.
Sensitivity Analysis script using Sobol method implemented in R.
GPU pricing of a cancellable swap, three ways: CUDA, ISO C++ stdpar, and JAX/XLA — Mark Joshi's kooderive modernized, rewritten twice, and cross-validated (LIBOR Market Model, Longstaff-Schwartz, AAD Greeks)
experiment with the quasi-random Sobol sequence
Random number generation for AWS Trainium via NKI (cuRAND-equivalent) — Philox counter-based RNG, standard distributions, Sobol / Halton / Latin-hypercube quasi-random sequences for Monte Carlo and QMC.
Python derivatives analytics with Monte Carlo and Sobol pricing, Black-Scholes validation, variance reduction, Greeks, implied volatility, and Streamlit.
Zero-dependency seeded key generation framework for Python — define parameter spaces, generate unique keys, and persist results.
Low-discrepancy (quasi-random) sequence generators for Scilab (Halton/Sobol/Faure/Niederreiter) — modernized to build on Scilab 2026.1.0
Quasi-Random Sequence Generators in Rust
Constrained non-convex optimization under a hard evaluation budget (Stanford AA222): a five-stage hybrid of penalty-method projected gradient, Sobol quasi-random sampling, and constraint-gradient nudging that returns feasible points on 499+ of 500 random starts, including a 10D problem with 8 constraints
To associate your repository with the sobol topic, visit your repo's landing page and select "manage topics."