Classical (values only)

Boltzmann(t_init, sigma)

Logarithmic cooling + Gaussian + Metropolis.

Fast(t_init, gamma)

Reciprocal cooling + Cauchy + Metropolis.

Gsa(t_init, =q_v, q_a)=

Tsallis cooling + Tsallis visit + Tsallis accept.

All called via run(obj, low, high, preset, n_epochs, steps_per_epoch, seed).

Pilot and low-discrepancy

  • pilot_draws_qmc(n, seed) -> (n,3) array of (T0, sigma, q_v).

  • low_discrepancy_points(low, high, n, skip=1) .

Polish

These drivers require gradients. Gradient support is provided by eindir; see the eindir gradients guide.

  • =polish(obj, grad, low, high, x0, max_fevals=200, …)

  • qmc_polish(obj, grad, low, high, n_starts, max_fevals_per_start, ...)

  • =shifted_qmc_polish(…, n_replicates=1, …)

Advanced drivers

  • additive_independence(obj, low, high, max_fevals, seed=0, degree=8, ... n_pilot=0) (values only, rank-1 surrogate).

  • gle_langevin(obj, grad, low, high, max_fevals, seed=0, omega0=0.2, dt=0.2, n_epochs=40) (gradient, colored noise).

Device and ensemble (same kernel)

  • run_device (single chain, NumPy or CuPy bounds)

  • run_ensemble (batched, n_chains, same kernel)

Hamiltonian Monte Carlo (HMC) / quasi-Monte Carlo (QMC) variants (also exposed)

  • run_hmc, run_qmc (see python/anneal/__init__.py and tests for current signatures).

All return dicts with best_pos, best_val, n_evals (or the rich History / DeviceHistory / EnsembleHistory objects from run / run_device).