def __init__(self, train_X: Tensor, train_Y: Tensor, train_Yvar: Tensor) -> None:
r"""A single-task exact GP model using a heteroskedastic noise model.
Args:
train_X: A `n x d` or `batch_shape x n x d` (batch mode) tensor of training
features.
train_Y: A `n x m` or `batch_shape x n x m` (batch mode) tensor of
training observations.
train_Yvar: A `batch_shape x n x m` or `batch_shape x n x m`
(batch mode) tensor of observed measurement noise.
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X).sum(dim=1, keepdim=True)
>>> se = torch.norm(train_X, dim=1, keepdim=True)
>>> train_Yvar = 0.1 + se * torch.rand_like(train_Y)
>>> model = HeteroskedasticSingleTaskGP(train_X, train_Y, train_Yvar)
"""
validate_input_scaling(train_X=train_X, train_Y=train_Y, train_Yvar=train_Yvar)
self._validate_tensor_args(X=train_X, Y=train_Y, Yvar=train_Yvar)
self._set_dimensions(train_X=train_X, train_Y=train_Y)
noise_likelihood = GaussianLikelihood(
noise_prior=SmoothedBoxPrior(-3, 5, 0.5, transform=torch.log),
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL, transform=None, initial_value=1.0
),
)
noise_model = SingleTaskGP(
train_X=train_X, train_Y=train_Yvar.log(), likelihood=noise_likelihood
)
likelihood = _GaussianLikelihoodBase(HeteroskedasticNoise(noise_model))
super().__init__(train_X=train_X, train_Y=train_Y, likelihood=likelihood)
self.to(train_X)
def __init__(self, train_X: Tensor, train_Y: Tensor, train_Yvar: Tensor) -> None:
r"""A single-task exact GP model using a heteroskedastic noise model.
Args:
train_X: A `n x d` or `batch_shape x n x d` (batch mode) tensor of training
features.
train_Y: A `n x (o)` or `batch_shape x n x (o)` (batch mode) tensor of
training observations.
train_Yvar: A `batch_shape x n x (o)` or `batch_shape x n x (o)`
(batch mode) tensor of observed measurement noise..
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X[:, 0]]) + torch.cos(train_X[:, 1])
>>> se = torch.norm(train_X - 0.5, dim=-1)
>>> train_Yvar = 0.1 + se * torch.rand_like(train_Y)
>>> model = HeteroskedasticSingleTaskGP(train_X, train_Y, train_Yvar)
"""
self._set_dimensions(train_X=train_X, train_Y=train_Y)
train_Y_log_var = torch.log(train_Yvar)
noise_likelihood = GaussianLikelihood(
noise_prior=SmoothedBoxPrior(-3, 5, 0.5, transform=torch.log),
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(MIN_INFERRED_NOISE_LEVEL, transform=None),
)
noise_model = SingleTaskGP(
train_X=train_X, train_Y=train_Y_log_var, likelihood=noise_likelihood
)
likelihood = _GaussianLikelihoodBase(HeteroskedasticNoise(noise_model))
super().__init__(train_X=train_X, train_Y=train_Y, likelihood=likelihood)
self.to(train_X)
def __init__(
self,
train_X: Tensor,
train_Y: Tensor,
likelihood: Optional[Likelihood] = None,
covar_module: Optional[Module] = None,
) -> None:
r"""A single-task exact GP model.
Args:
train_X: A `n x d` or `batch_shape x n x d` (batch mode) tensor of training
features.
train_Y: A `n x m` or `batch_shape x n x m` (batch mode) tensor of
training observations.
likelihood: A likelihood. If omitted, use a standard
GaussianLikelihood with inferred noise level.
covar_module: The covariance (kernel) matrix. If omitted, use the
MaternKernel.
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X).sum(dim=1, keepdim=True)
>>> model = SingleTaskGP(train_X, train_Y)
"""
validate_input_scaling(train_X=train_X, train_Y=train_Y)
self._validate_tensor_args(X=train_X, Y=train_Y)
self._set_dimensions(train_X=train_X, train_Y=train_Y)
train_X, train_Y, _ = self._transform_tensor_args(X=train_X, Y=train_Y)
if likelihood is None:
noise_prior = GammaPrior(1.1, 0.05)
noise_prior_mode = (noise_prior.concentration -
1) / noise_prior.rate
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=noise_prior_mode,
),
)
else:
self._is_custom_likelihood = True
ExactGP.__init__(self, train_X, train_Y, likelihood)
self.mean_module = ConstantMean(batch_shape=self._aug_batch_shape)
if covar_module is None:
self.covar_module = ScaleKernel(
MaternKernel(
nu=2.5,
ard_num_dims=train_X.shape[-1],
batch_shape=self._aug_batch_shape,
lengthscale_prior=GammaPrior(3.0, 6.0),
),
batch_shape=self._aug_batch_shape,
outputscale_prior=GammaPrior(2.0, 0.15),
)
else:
self.covar_module = covar_module
self.to(train_X)
def __init__(
self,
train_X: Tensor,
train_Y: Tensor,
train_Yvar: Tensor,
outcome_transform: Optional[OutcomeTransform] = None,
) -> None:
r"""A single-task exact GP model using a heteroskedastic noise model.
Args:
train_X: A `batch_shape x n x d` tensor of training features.
train_Y: A `batch_shape x n x m` tensor of training observations.
train_Yvar: A `batch_shape x n x m` tensor of observed measurement
noise.
outcome_transform: An outcome transform that is applied to the
training data during instantiation and to the posterior during
inference (that is, the `Posterior` obtained by calling
`.posterior` on the model will be on the original scale).
Note that the noise model internally log-transforms the
variances, which will happen after this transform is applied.
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X).sum(dim=1, keepdim=True)
>>> se = torch.norm(train_X, dim=1, keepdim=True)
>>> train_Yvar = 0.1 + se * torch.rand_like(train_Y)
>>> model = HeteroskedasticSingleTaskGP(train_X, train_Y, train_Yvar)
"""
if outcome_transform is not None:
train_Y, train_Yvar = outcome_transform(train_Y, train_Yvar)
validate_input_scaling(train_X=train_X,
train_Y=train_Y,
train_Yvar=train_Yvar)
self._validate_tensor_args(X=train_X, Y=train_Y, Yvar=train_Yvar)
self._set_dimensions(train_X=train_X, train_Y=train_Y)
noise_likelihood = GaussianLikelihood(
noise_prior=SmoothedBoxPrior(-3, 5, 0.5, transform=torch.log),
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=1.0),
)
noise_model = SingleTaskGP(
train_X=train_X,
train_Y=train_Yvar,
likelihood=noise_likelihood,
outcome_transform=Log(),
)
likelihood = _GaussianLikelihoodBase(HeteroskedasticNoise(noise_model))
super().__init__(train_X=train_X,
train_Y=train_Y,
likelihood=likelihood)
self.register_added_loss_term("noise_added_loss")
self.update_added_loss_term("noise_added_loss",
NoiseModelAddedLossTerm(noise_model))
if outcome_transform is not None:
self.outcome_transform = outcome_transform
self.to(train_X)
def __init__(self,
train_X: Tensor,
train_Y: Tensor,
likelihood: Optional[Likelihood] = None) -> None:
r"""A single-task exact GP model.
Args:
train_X: A `n x d` or `batch_shape x n x d` (batch mode) tensor of training
features.
train_Y: A `n x (o)` or `batch_shape x n x (o)` (batch mode) tensor of
training observations.
likelihood: A likelihood. If omitted, use a standard
GaussianLikelihood with inferred noise level.
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X[:, 0]) + torch.cos(train_X[:, 1])
>>> model = SingleTaskGP(train_X, train_Y)
"""
ard_num_dims = train_X.shape[-1]
train_X, train_Y, _ = self._set_dimensions(train_X=train_X,
train_Y=train_Y)
train_X, train_Y, _ = multioutput_to_batch_mode_transform(
train_X=train_X, train_Y=train_Y, num_outputs=self._num_outputs)
if likelihood is None:
noise_prior = GammaPrior(1.1, 0.05)
noise_prior_mode = (noise_prior.concentration -
1) / noise_prior.rate
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=noise_prior_mode,
),
)
else:
self._likelihood_state_dict = deepcopy(likelihood.state_dict())
ExactGP.__init__(self, train_X, train_Y, likelihood)
self.mean_module = ConstantMean(batch_shape=self._aug_batch_shape)
self.covar_module = ScaleKernel(
MaternKernel(
nu=2.5,
ard_num_dims=ard_num_dims,
batch_shape=self._aug_batch_shape,
lengthscale_prior=GammaPrior(3.0, 6.0),
),
batch_shape=self._aug_batch_shape,
outputscale_prior=GammaPrior(2.0, 0.15),
)
self.to(train_X)
def update(self, context, actions, rewards):
self.x.append(context)
self.y.append(actions if rewards > 0 else abs(actions-1))
# if rewards > 0:
# self.y.append(actions)
# elif rewards == 0:
# self.y.append(0.5)
# elif rewards < 0:
# self.y.append(abs(actions-1))
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=noise_prior_mode,
),
)
self.model = GPRegressionModel(torch.Tensor(self.x).to(device), torch.Tensor(self.y).to(device), likelihood).to(device)
mll = ExactMarginalLogLikelihood(likelihood, self.model).to(device)
fit_gpytorch_model(mll, optimizer=fit_gpytorch_torch)
def fit_gp(self) -> None:
"""
Re-fits the GP using the most up to date data.
"""
noise_prior = GammaPrior(1.1, 0.5)
noise_prior_mode = (noise_prior.concentration - 1) / noise_prior.rate
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
batch_shape=[],
noise_constraint=GreaterThan(
# 0.000005, # minimum observation noise assumed in the GP model
0.0001,
transform=None,
initial_value=noise_prior_mode,
),
)
self.model = SingleTaskGP(
self.X, self.Y, likelihood, outcome_transform=Standardize(m=1)
)
mll = ExactMarginalLogLikelihood(self.model.likelihood, self.model)
fit_gpytorch_model(mll)
# dummy computation to be safe with gp fit
try:
dummy = torch.rand(
(1, self.q, self.dim), dtype=self.dtype, device=self.device
)
_ = self.model.posterior(dummy).mean
except RuntimeError as err:
if self.fit_count < 5:
self.fit_count += 1
self.Y = self.Y + torch.randn_like(self.Y) * 0.001
self.fit_gp()
else:
raise err
self.fit_count = 0
self.passed = False
def initialize_model(self, train_X, train_Y, state_dict=None):
"""Initialise model for BO."""
# From: https://github.com/pytorch/botorch/issues/179
noise_prior = GammaPrior(1.1, 0.05)
noise_prior_mode = (noise_prior.concentration - 1) / noise_prior.rate
MIN_INFERRED_NOISE_LEVEL = 1e-3
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=noise_prior_mode,
),
)
# train_x = self.scale_to_0_1_bounds(train_X)
train_Y = standardize(train_Y)
gp = SingleTaskGP(train_X, train_Y, likelihood=likelihood)
mll = ExactMarginalLogLikelihood(gp.likelihood, gp)
# load state dict if it is passed
if state_dict is not None:
gp.load_state_dict(state_dict)
return mll, gp
def __init__(
self,
train_X: Tensor,
train_Y: Tensor,
likelihood: Optional[Likelihood] = None,
covar_module: Optional[Module] = None,
outcome_transform: Optional[OutcomeTransform] = None,
) -> None:
r"""A single-task exact GP model.
Args:
train_X: A `batch_shape x n x d` tensor of training features.
train_Y: A `batch_shape x n x m` tensor of training observations.
likelihood: A likelihood. If omitted, use a standard
GaussianLikelihood with inferred noise level.
covar_module: The module computing the covariance (Kernel) matrix.
If omitted, use a `MaternKernel`.
outcome_transform: An outcome transform that is applied to the
training data during instantiation and to the posterior during
inference (that is, the `Posterior` obtained by calling
`.posterior` on the model will be on the original scale).
Example:
>>> train_X = torch.rand(20, 2)
>>> train_Y = torch.sin(train_X).sum(dim=1, keepdim=True)
>>> model = SingleTaskGP(train_X, train_Y)
"""
if outcome_transform is not None:
train_Y, _ = outcome_transform(train_Y)
validate_input_scaling(train_X=train_X, train_Y=train_Y)
self._validate_tensor_args(X=train_X, Y=train_Y)
self._set_dimensions(train_X=train_X, train_Y=train_Y)
train_X, train_Y, _ = self._transform_tensor_args(X=train_X, Y=train_Y)
if likelihood is None:
noise_prior = GammaPrior(1.1, 0.05)
noise_prior_mode = (noise_prior.concentration -
1) / noise_prior.rate
likelihood = GaussianLikelihood(
noise_prior=noise_prior,
batch_shape=self._aug_batch_shape,
noise_constraint=GreaterThan(
MIN_INFERRED_NOISE_LEVEL,
transform=None,
initial_value=noise_prior_mode,
),
)
else:
self._is_custom_likelihood = True
ExactGP.__init__(self, train_X, train_Y, likelihood)
self.mean_module = ConstantMean(batch_shape=self._aug_batch_shape)
if covar_module is None:
self.covar_module = ScaleKernel(
MaternKernel(
nu=2.5,
ard_num_dims=train_X.shape[-1],
batch_shape=self._aug_batch_shape,
lengthscale_prior=GammaPrior(3.0, 6.0),
),
batch_shape=self._aug_batch_shape,
outputscale_prior=GammaPrior(2.0, 0.15),
)
self._subset_batch_dict = {
"likelihood.noise_covar.raw_noise": -2,
"mean_module.constant": -2,
"covar_module.raw_outputscale": -1,
"covar_module.base_kernel.raw_lengthscale": -3,
}
else:
self.covar_module = covar_module
# TODO: Allow subsetting of other covar modules
if outcome_transform is not None:
self.outcome_transform = outcome_transform
self.to(train_X)