torch_numopt.curvature package#

Submodules#

Module contents#

Curvature estimators for second-order optimization.

This package provides classes that approximate or compute the Hessian matrix (and its products) in various ways:

  • Exact Hessian (full or block-diagonal)

  • Gauss-Newton approximation (full or block)

  • Hutchinson diagonal approximation (via random projections)

  • Identity (no curvature)

All estimators inherit from CurvatureEstimator and implement the scaling_matrix, hvp, and quadratic_form methods.

class NaiveIdentityCalculator[source]#

Bases: CurvatureEstimator

Curvature estimator that always returns the identity matrix.

The scaling matrix is 1 (scalar), the Hessian-vector product is the vector itself, and the quadratic form is the squared norm.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, step_dir)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Obtain the curvature matrix in its native representation.

update()

Updates the parameters of the curvature estimator.

scaling_matrix(objective, params)[source]#

Obtain the curvature matrix in its native representation.

Return type:

float

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

Returns:
iterable or torch.Tensor

Representation of the matrix (scalar, vector, tuple of blocks, or full tensor).

hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Return type:

Iterable[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, step_dir)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tensor

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

class ExactHessianCalculator(damping=None, mu=0.0001)[source]#

Bases: CurvatureEstimator

Compute the exact Hessian matrix (full or block) of the objective.

The Hessian is obtained using torch.func.hessian, which computes the full second-order derivatives. For large models, this can be memory- intensive; use the block version for parameter groups.

Parameters:
dampingstr or None, default=None

Damping strategy: "identity" adds mu * I, "fletcher" adds mu * diag(H). If None, no damping is applied.

mufloat, default=1e-4

Damping coefficient.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, grad_params)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Calculation of the exact hessian of the Neural network given a dataset.

update()

Updates the parameters of the curvature estimator.

scaling_matrix(objective, params)[source]#

Calculation of the exact hessian of the Neural network given a dataset.

Return type:

Tuple[Tensor]

Parameters:
x: torch.Tensor

Input dataset for calculating the loss.

y: torch.Tensor

Target dataset for calculating the loss.

loss_fn: torch.Module

Loss function for which to calculate the hessian.

vectorize: boolean

Use vectorization in pytorch’s implementation of the hessian calculation.

hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, grad_params)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tensor

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

class ExactBlockHessianCalculator(damping=None, mu=0.0001)[source]#

Bases: CurvatureEstimator

Exact Hessian approximated as a block-diagonal matrix.

Each block corresponds to a single parameter tensor (e.g., a weight matrix). This is often sufficient for many optimization problems and is cheaper than the full Hessian.

Parameters:
dampingstr or None, default=None

Damping strategy (see ExactHessianCalculator).

mufloat, default=1e-4

Damping coefficient.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, grad_params)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Calculation of the exact hessian of the Neural network given a dataset.

update()

Updates the parameters of the curvature estimator.

scaling_matrix(objective, params)[source]#

Calculation of the exact hessian of the Neural network given a dataset.

Return type:

Tuple[Tensor]

Parameters:
x: torch.Tensor

Input dataset for calculating the loss.

y: torch.Tensor

Target dataset for calculating the loss.

loss_fn: torch.Module

Loss function for which to calculate the hessian.

vectorize: boolean

Use vectorization in pytorch’s implementation of the hessian calculation.

hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, grad_params)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tensor

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

class GaussNewtonApproximation(vectorize=True, damping=None, mu=0.0001)[source]#

Bases: CurvatureEstimator

Full Gauss-Newton Hessian approximation.

The matrix is computed as Jᵀ J, where J is the Jacobian of the residual vector with respect to the parameters. This estimator forms a single dense matrix.

Parameters:
vectorizebool, default=True

If True, use vectorized Jacobian computation (may be faster).

dampingstr or None, default=None

Damping strategy (identity or Fletcher).

mufloat, default=1e-4

Damping coefficient.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, grad_params)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Calculation of the an approximate hessian of the Neural network given a dataset as in the Gauss-Newton algorithm.

update()

Updates the parameters of the curvature estimator.

jvp

scaling_matrix(objective, params)[source]#

Calculation of the an approximate hessian of the Neural network given a dataset as in the Gauss-Newton algorithm. The approximate Hessian is calculated as the square of the Jacobian of the residual of every data point with respect to the parameters.

Let the loss function be, for example the MSE:

\(\mathcal{L}(x,y;\theta) = \sum^{N}_{i=1} (f(x_i; \theta) - y_i)^2 = \sum^{N}_{i=1} r_i\)

Then the Jacobian of the residuals will be the matrix:

\((J_{\theta}[\mathcal{L}])_{i,j} = \dfrac{\partial r_i}{\partial \theta_j}\)

Then, we will approximate the hessian as the product of the Jacobian with it’s transpose, noting that the result will be a square matrix with size \(p\\times p\) with \(p\) being the number of parameters of the model:

\(H_{\theta}[\mathcal{L}] \approx J_{\theta}[\mathcal{L}]^{\intercal} \cdot J_{\theta}[\mathcal{L}]\)

Return type:

Tuple[Tensor]

Parameters:
x: torch.Tensor

Input dataset for calculating the loss.

y: torch.Tensor

Target dataset for calculating the loss.

loss_fn: torch.Module

Loss function for which to calculate the hessian.

vectorize: boolean

Use vectorization in pytorch’s implementation of the hessian calculation.

jvp(objective, params, step_dir)[source]#
hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, grad_params)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

class GaussNewtonBlockApproximation(vectorize=True, damping=None, mu=0.0001)[source]#

Bases: CurvatureEstimator

Block-diagonal Gauss-Newton Hessian approximation.

Each block is formed as J_iᵀ J_i, where J_i is the Jacobian of the residual with respect to the i-th parameter group. Cross-group derivatives are ignored.

Parameters:
vectorizebool, default=True

Use vectorized Jacobian computation.

dampingstr or None, default=None

Damping strategy.

mufloat, default=1e-4

Damping coefficient.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, grad_params)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Calculation of the an approximate hessian of the Neural network given a dataset as in the Gauss-Newton algorithm.

update()

Updates the parameters of the curvature estimator.

jvp

scaling_matrix(objective, params)[source]#

Calculation of the an approximate hessian of the Neural network given a dataset as in the Gauss-Newton algorithm. The approximate Hessian is calculated as the square of the Jacobian of the residual of every data point with respect to the parameters.

Let the loss function be, for example the MSE:

\(\mathcal{L}(x,y;\theta) = \sum^{N}_{i=1} (f(x_i; \theta) - y_i)^2 = \sum^{N}_{i=1} r_i\)

Then the Jacobian of the residuals will be the matrix:

\((J_{\theta}[\mathcal{L}])_{i,j} = \dfrac{\partial r_i}{\partial \theta_j}\)

Then, we will approximate the hessian as the product of the Jacobian with it’s transpose, noting that the result will be a square matrix with size \(p\\times p\) with \(p\) being the number of parameters of the model:

\(H_{\theta}[\mathcal{L}] \approx J_{\theta}[\mathcal{L}]^{\intercal} \cdot J_{\theta}[\mathcal{L}]\)

Return type:

Tuple[Tensor]

Parameters:
x: torch.Tensor

Input dataset for calculating the loss.

y: torch.Tensor

Target dataset for calculating the loss.

loss_fn: torch.Module

Loss function for which to calculate the hessian.

vectorize: boolean

Use vectorization in pytorch’s implementation of the hessian calculation.

jvp(objective, params, step_dir)[source]#
hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, grad_params)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

class HutchinsonDiagonalApproximation(n_samples=1, skip_iters=0)[source]#

Bases: CurvatureEstimator

Diagonal Hessian estimator via Hutchinson’s method.

The diagonal is estimated as the average of z ⊙ (H z) over random Rademacher vectors z.

Parameters:
n_samplesint, default=1

Number of random samples to average.

Methods

full_scaling_matrix(objective, params)

Return the curvature matrix as a single dense tensor.

hvp(objective, params, step_dir)

Compute the Hessian-vector product H * v.

quadratic_form(objective, params, step_dir)

Compute the quadratic form vᵀ H v.

reset()

Reset any internal state (intended to be used for quasi-Newton methods).

scaling_matrix(objective, params)

Obtain the curvature matrix in its native representation.

update()

Updates the parameters of the curvature estimator.

scaling_matrix(objective, params)[source]#

Obtain the curvature matrix in its native representation.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

Returns:
iterable or torch.Tensor

Representation of the matrix (scalar, vector, tuple of blocks, or full tensor).

hvp(objective, params, step_dir)[source]#

Compute the Hessian-vector product H * v.

Return type:

Tuple[Tensor]

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v (same structure as params).

Returns:
Params

Result of H * v.

quadratic_form(objective, params, step_dir)[source]#

Compute the quadratic form vᵀ H v.

Return type:

Tensor

Parameters:
objectiveObjectiveFunction

Objective function.

paramsParams

Parameter tensors.

step_dirParams

Vector v.

Returns:
torch.Tensor

Scalar value vᵀ H v.

update()[source]#

Updates the parameters of the curvature estimator.