def test_posterior_latent_gp_and_likelihood_without_optimization(self, cuda=False):
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
with gpytorch.settings.debug(False):
# We're manually going to set the hyperparameters to be ridiculous
likelihood = FixedNoiseGaussianLikelihood(torch.ones(11) * 1e-8)
gp_model = ExactGPModel(train_x, train_y, likelihood)
# Update lengthscale prior to accommodate extreme parameters
gp_model.rbf_covar_module.initialize(lengthscale=exp(-6))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Compute posterior distribution
gp_model.eval()
likelihood.eval()
# Let's see how our model does, conditioned with weird hyperparams
# The posterior should fit all the data
function_predictions = likelihood(gp_model(train_x))
self.assertLess(torch.norm(function_predictions.mean - train_y), 1e-3)
self.assertLess(torch.norm(function_predictions.variance), 5e-3)
# It shouldn't fit much else though
test_function_predictions = gp_model(torch.tensor([1.1]).type_as(test_x))
self.assertLess(torch.norm(test_function_predictions.mean - 0), 1e-4)
self.assertLess(torch.norm(test_function_predictions.variance - gp_model.covar_module.outputscale), 1e-4)
def test_fixed_noise_fantasy_updates_batch(self, cuda=False):
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
noise = torch.full_like(train_y, 2e-4)
test_noise = torch.full_like(test_y, 3e-4)
likelihood = FixedNoiseGaussianLikelihood(noise)
gp_model = ExactGPModel(train_x, train_y, likelihood)
mll = gpytorch.ExactMarginalLogLikelihood(likelihood, gp_model)
gp_model.covar_module.base_kernel.initialize(lengthscale=exp(1))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Find optimal model hyperparameters
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) + list(likelihood.parameters()), lr=0.15)
for _ in range(50):
optimizer.zero_grad()
with gpytorch.settings.debug(False):
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
optimizer.step()
with gpytorch.settings.fast_pred_var():
# Test the model
gp_model.eval()
likelihood.eval()
test_function_predictions = likelihood(gp_model(test_x), noise=test_noise)
# Cut data down, and then add back via the fantasy interface
gp_model.set_train_data(train_x[:5], train_y[:5], strict=False)
gp_model.likelihood.noise_covar = FixedGaussianNoise(noise=noise[:5])
likelihood(gp_model(test_x), noise=test_noise)
fantasy_x = train_x[5:].clone().unsqueeze(0).unsqueeze(-1).repeat(3, 1, 1).requires_grad_(True)
fantasy_y = train_y[5:].unsqueeze(0).repeat(3, 1)
fant_model = gp_model.get_fantasy_model(fantasy_x, fantasy_y, noise=noise[5:].unsqueeze(0).repeat(3, 1))
fant_function_predictions = likelihood(fant_model(test_x), noise=test_noise)
self.assertAllClose(test_function_predictions.mean, fant_function_predictions.mean[0], atol=1e-4)
fant_function_predictions.mean.sum().backward()
self.assertTrue(fantasy_x.grad is not None)
def test_posterior_latent_gp_and_likelihood_with_optimization(
self, cuda=False):
# This test throws a warning because the fixed noise likelihood gets the wrong input
warnings.simplefilter("ignore", GPInputWarning)
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
# We're manually going to set the hyperparameters to something they shouldn't be
likelihood = FixedNoiseGaussianLikelihood(torch.ones(11) * 0.001)
gp_model = ExactGPModel(train_x, train_y, likelihood)
mll = gpytorch.ExactMarginalLogLikelihood(likelihood, gp_model)
gp_model.rbf_covar_module.initialize(lengthscale=exp(1))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Find optimal model hyperparameters
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(75):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
optimizer.step()
# Test the model
gp_model.eval()
likelihood.eval()
test_function_predictions = likelihood(gp_model(test_x))
mean_abs_error = torch.mean(
torch.abs(test_y - test_function_predictions.mean))
self.assertLess(mean_abs_error.squeeze().item(), 0.05)
def test_kissgp_gp_fast_pred_var(self):
with gpytorch.settings.fast_pred_var(), gpytorch.settings.debug(False):
train_x, train_y, test_x, test_y = make_data()
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) * 0.001)
gp_model = GPRegressionModel(train_x, train_y, likelihood)
mll = gpytorch.mlls.ExactMarginalLogLikelihood(
likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
# Set the cache
test_function_predictions = likelihood(gp_model(train_x))
# Now bump up the likelihood to something huge
# This will make it easy to calculate the variance
likelihood.initialize(noise=3.)
test_function_predictions = likelihood(gp_model(train_x))
noise = likelihood.noise
var_diff = (test_function_predictions.variance - noise).abs()
self.assertLess(torch.max(var_diff / noise), 0.05)
def test_kissgp_gp_mean_abs_error_cuda(self):
if not torch.cuda.is_available():
return
with least_used_cuda_device():
train_x, train_y, test_x, test_y = make_data(cuda=True)
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) *
0.001).cuda()
gp_model = GPRegressionModel(train_x, train_y, likelihood).cuda()
mll = gpytorch.mlls.ExactMarginalLogLikelihood(
likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
test_preds = likelihood(gp_model(test_x)).mean
mean_abs_error = torch.mean(torch.abs(test_y - test_preds))
self.assertLess(mean_abs_error.squeeze().item(), 0.02)
def test_kissgp_gp_mean_abs_error(self):
# This test throws a warning because the fixed noise likelihood gets the wrong input
warnings.simplefilter("ignore", GPInputWarning)
train_x, train_y, test_x, test_y = make_data()
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) * 0.001)
gp_model = GPRegressionModel(train_x, train_y, likelihood)
mll = gpytorch.mlls.ExactMarginalLogLikelihood(likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
test_preds = likelihood(gp_model(test_x)).mean
mean_abs_error = torch.mean(torch.abs(test_y - test_preds))
self.assertLess(mean_abs_error.squeeze().item(), 0.05)