Skip to content

Funcsgd

sgd(*, center_init, center_learning_rate, momentum=None)

Initialize the gradient ascent/descent search and get its initial state.

Reference regarding the momentum behavior:

Polyak, B. T. (1964).
Some methods of speeding up the convergence of iteration methods.
USSR Computational Mathematics and Mathematical Physics, 4(5):1–17.

Parameters:

Name Type Description Default
center_init BatchableVector

Starting point for the gradient ascent/descent. Expected as a PyTorch tensor with at least 1 dimension. If there are 2 or more dimensions, the extra leftmost dimensions are interpreted as batch dimensions.

 required
center_learning_rate BatchableScalar

Learning rate (i.e. the step size) for gradient ascent/descent. Can be a scalar or a multidimensional tensor. If given as a tensor with multiple dimensions, those dimensions will be interpreted as batch dimensions.

 required
momentum Optional[BatchableScalar]

Momentum coefficient, expected as a scalar. If provided as a scalar, Polyak-style momentum will be enabled. If given as a tensor with multiple dimensions, those dimensions will be interpreted as batch dimensions.

 None
Source code in evotorch/algorithms/functional/funcsgd.py 
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
def sgd(
    *,
    center_init: BatchableVector,
    center_learning_rate: BatchableScalar,
    momentum: Optional[BatchableScalar] = None,
) -> SGDState:
    """
    Initialize the gradient ascent/descent search and get its initial state.

    Reference regarding the momentum behavior:

        Polyak, B. T. (1964).
        Some methods of speeding up the convergence of iteration methods.
        USSR Computational Mathematics and Mathematical Physics, 4(5):1–17.

    Args:
        center_init: Starting point for the gradient ascent/descent.
            Expected as a PyTorch tensor with at least 1 dimension.
            If there are 2 or more dimensions, the extra leftmost dimensions
            are interpreted as batch dimensions.
        center_learning_rate: Learning rate (i.e. the step size) for gradient
            ascent/descent. Can be a scalar or a multidimensional tensor.
            If given as a tensor with multiple dimensions, those dimensions
            will be interpreted as batch dimensions.
        momentum: Momentum coefficient, expected as a scalar.
            If provided as a scalar, Polyak-style momentum will be enabled.
            If given as a tensor with multiple dimensions, those dimensions
            will be interpreted as batch dimensions.
    """
    center_init = torch.as_tensor(center_init)
    dtype = center_init.dtype
    device = center_init.device

    def as_tensor(x) -> torch.Tensor:
        return torch.as_tensor(x, dtype=dtype, device=device)

    velocity = torch.zeros_like(center_init)
    center_learning_rate = as_tensor(center_learning_rate)
    momentum = as_tensor(0.0) if momentum is None else as_tensor(momentum)

    return SGDState(
        center=center_init,
        velocity=velocity,
        center_learning_rate=center_learning_rate,
        momentum=momentum,
    )

sgd_ask(state)

Get the search point stored by the given SGDState.

Parameters:

Name Type Description Default
state SGDState

The current state of gradient ascent/descent.

 required
Source code in evotorch/algorithms/functional/funcsgd.py 
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
def sgd_ask(state: SGDState) -> torch.Tensor:
    """
    Get the search point stored by the given `SGDState`.

    Args:
        state: The current state of gradient ascent/descent.
    Returns:
        The search point as a 1-dimensional tensor in the non-batched case,
        or as a multi-dimensional tensor if the search is batched.
    """
    return state.center

sgd_tell(state, *, follow_grad)

Tell the gradient ascent/descent the current gradient to get its next state.

Parameters:

Name Type Description Default
state SGDState

The current state of gradient ascent/descent.

 required
follow_grad BatchableVector

Gradient at the current point of the search. Can be a 1-dimensional tensor in the non-batched case, or a multi-dimensional tensor in the batched case.

 required
Source code in evotorch/algorithms/functional/funcsgd.py 
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
def sgd_tell(state: SGDState, *, follow_grad: BatchableVector) -> SGDState:
    """
    Tell the gradient ascent/descent the current gradient to get its next state.

    Args:
        state: The current state of gradient ascent/descent.
        follow_grad: Gradient at the current point of the search.
            Can be a 1-dimensional tensor in the non-batched case,
            or a multi-dimensional tensor in the batched case.
    Returns:
        The updated state of gradient ascent/descent, with the given gradient
        applied.
    """
    velocity, center = _sgd_step(
        follow_grad,
        state.center,
        state.velocity,
        state.center_learning_rate,
        state.momentum,
    )

    return SGDState(
        center=center,
        velocity=velocity,
        center_learning_rate=state.center_learning_rate,
        momentum=state.momentum,
    )