def run_inference(model, args, rng_key, X, Y): start = time.time() # demonstrate how to use different HMC initialization strategies if args.init_strategy == "value": init_strategy = init_to_value(values={ "kernel_var": 1.0, "kernel_noise": 0.05, "kernel_length": 0.5 }) elif args.init_strategy == "median": init_strategy = init_to_median(num_samples=10) elif args.init_strategy == "feasible": init_strategy = init_to_feasible() elif args.init_strategy == "sample": init_strategy = init_to_sample() elif args.init_strategy == "uniform": init_strategy = init_to_uniform(radius=1) kernel = NUTS(model, init_strategy=init_strategy) mcmc = MCMC( kernel, args.num_warmup, args.num_samples, num_chains=args.num_chains, progress_bar=False if "NUMPYRO_SPHINXBUILD" in os.environ else True) mcmc.run(rng_key, X, Y) mcmc.print_summary() print('\nMCMC elapsed time:', time.time() - start) return mcmc.get_samples()
def run_hmc(rng_key, model, data, num_mix_comp, args, bvm_init_locs): kernel = NUTS(model, init_strategy=init_to_value(values=bvm_init_locs), max_tree_depth=7) mcmc = MCMC(kernel, num_samples=args.num_samples, num_warmup=args.num_warmup) mcmc.run(rng_key, data, len(data), num_mix_comp) mcmc.print_summary() post_samples = mcmc.get_samples() return post_samples
def run_hmc(model, data, num_mix_comp, num_samples, bvm_init_locs): rng_key = random.PRNGKey(0) kernel = NUTS( model, init_strategy=init_to_value(values=bvm_init_locs), dense_mass=True, max_tree_depth=5, ) mcmc = MCMC(kernel, num_samples=num_samples, num_warmup=num_samples // 5) mcmc.run(rng_key, data, len(data), num_mix_comp) mcmc.print_summary() post_samples = mcmc.get_samples() return post_samples
def benchmark_hmc(args, features, labels): rng_key = random.PRNGKey(1) start = time.time() # a MAP estimate at the following source # https://github.com/google/edward2/blob/master/examples/no_u_turn_sampler/logistic_regression.py#L117 ref_params = { "coefs": jnp.array([ +2.03420663e00, -3.53567265e-02, -1.49223924e-01, -3.07049364e-01, -1.00028366e-01, -1.46827862e-01, -1.64167881e-01, -4.20344204e-01, +9.47479829e-02, -1.12681836e-02, +2.64442056e-01, -1.22087866e-01, -6.00568838e-02, -3.79419506e-01, -1.06668741e-01, -2.97053963e-01, -2.05253899e-01, -4.69537191e-02, -2.78072730e-02, -1.43250525e-01, -6.77954629e-02, -4.34899796e-03, +5.90927452e-02, +7.23133609e-02, +1.38526391e-02, -1.24497898e-01, -1.50733739e-02, -2.68872194e-02, -1.80925727e-02, +3.47936489e-02, +4.03552800e-02, -9.98773426e-03, +6.20188080e-02, +1.15002751e-01, +1.32145107e-01, +2.69109547e-01, +2.45785132e-01, +1.19035013e-01, -2.59744357e-02, +9.94279515e-04, +3.39266285e-02, -1.44057125e-02, -6.95222765e-02, -7.52013028e-02, +1.21171586e-01, +2.29205526e-02, +1.47308692e-01, -8.34354162e-02, -9.34122875e-02, -2.97472421e-02, -3.03937674e-01, -1.70958012e-01, -1.59496680e-01, -1.88516974e-01, -1.20889175e00, ]) } if args.algo == "HMC": step_size = jnp.sqrt(0.5 / features.shape[0]) trajectory_length = step_size * args.num_steps kernel = HMC( model, step_size=step_size, trajectory_length=trajectory_length, adapt_step_size=False, dense_mass=args.dense_mass, ) subsample_size = None elif args.algo == "NUTS": kernel = NUTS(model, dense_mass=args.dense_mass) subsample_size = None elif args.algo == "HMCECS": subsample_size = 1000 inner_kernel = NUTS( model, init_strategy=init_to_value(values=ref_params), dense_mass=args.dense_mass, ) # note: if num_blocks=100, we'll update 10 index at each MCMC step # so it took 50000 MCMC steps to iterative the whole dataset kernel = HMCECS(inner_kernel, num_blocks=100, proxy=HMCECS.taylor_proxy(ref_params)) elif args.algo == "SA": # NB: this kernel requires large num_warmup and num_samples # and running on GPU is much faster than on CPU kernel = SA(model, adapt_state_size=1000, init_strategy=init_to_value(values=ref_params)) subsample_size = None elif args.algo == "FlowHMCECS": subsample_size = 1000 guide = AutoBNAFNormal(model, num_flows=1, hidden_factors=[8]) svi = SVI(model, guide, numpyro.optim.Adam(0.01), Trace_ELBO()) svi_result = svi.run(random.PRNGKey(2), 2000, features, labels) params, losses = svi_result.params, svi_result.losses plt.plot(losses) plt.show() neutra = NeuTraReparam(guide, params) neutra_model = neutra.reparam(model) neutra_ref_params = {"auto_shared_latent": jnp.zeros(55)} # no need to adapt mass matrix if the flow does a good job inner_kernel = NUTS( neutra_model, init_strategy=init_to_value(values=neutra_ref_params), adapt_mass_matrix=False, ) kernel = HMCECS(inner_kernel, num_blocks=100, proxy=HMCECS.taylor_proxy(neutra_ref_params)) else: raise ValueError( "Invalid algorithm, either 'HMC', 'NUTS', or 'HMCECS'.") mcmc = MCMC(kernel, num_warmup=args.num_warmup, num_samples=args.num_samples) mcmc.run(rng_key, features, labels, subsample_size, extra_fields=("accept_prob", )) print("Mean accept prob:", jnp.mean(mcmc.get_extra_fields()["accept_prob"])) mcmc.print_summary(exclude_deterministic=False) print("\nMCMC elapsed time:", time.time() - start)
height=df.height.values, br_positive=False) p6_1, losses = svi.run(random.PRNGKey(0), 2000) post_laplace = m6_1.sample_posterior(random.PRNGKey(1), p6_1, (1000, )) analyze_post(post_laplace, 'laplace') # MCMC fit # code from p298 (code 9.28) of rethinking2 #https://fehiepsi.github.io/rethinking-numpyro/09-markov-chain-monte-carlo.html kernel = NUTS( model, init_strategy=init_to_value(values={ "a": 10.0, "bl": 0.0, "br": 0.1, "sigma": 1.0 }), ) mcmc = MCMC(kernel, num_warmup=500, num_samples=500, num_chains=4) # df.T has size 3x100 data_dict = dict(zip(df.columns, df.T.values)) data_dict['br_positive'] = False mcmc.run(random.PRNGKey(0), **data_dict) mcmc.print_summary() post_hmc = mcmc.get_samples() analyze_post(post_hmc, 'hmc') # Constrained model where beta_r >= 0