# tfl.lattice_lib.project_by_dykstra

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_lib.py#L1830-L2071) |

Applies dykstra's projection algorithm for monotonicity/trust constraints.

    tfl.lattice_lib.project_by_dykstra(
        weights,
        lattice_sizes,
        monotonicities=None,
        unimodalities=None,
        edgeworth_trusts=None,
        trapezoid_trusts=None,
        monotonic_dominances=None,
        range_dominances=None,
        joint_monotonicities=None,
        joint_unimodalities=None,
        num_iterations=1
    )

- Returns honest projection with respect to L2 norm if num_iterations is inf.
- Monotonicity will be violated by some small eps(num_iterations).
- Complexity: O(num_iterations \* (num_monotonic_dims + num_trust_constraints)
  - num_lattice_weights)

Dykstra's alternating projections algorithm projects into intersection of
several convex sets. For algorithm description itself use Google or Wiki:
<https://en.wikipedia.org/wiki/Dykstra%27s_projection_algorithm>

Here, each monotonicity constraint is split up into 2 independent convex sets
each trust constraint is split up into 4 independent convex sets. These sets
are then projected onto exactly (in L2 space). For more details, see the
_project*partial*\* functions.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `weights` | `Lattice` weights tensor of shape: `(prod(lattice_sizes), units)`. |
| `lattice_sizes` | list or tuple of integers which represents lattice sizes. which correspond to weights. |
| `monotonicities` | None or list or tuple of same length as lattice_sizes of {0, 1} which represents monotonicity constraints per dimension. 1 stands for increasing (non-decreasing in fact), 0 for no monotonicity constraints. |
| `unimodalities` | None or list or tuple of same length as lattice_sizes of {-1, 0, 1} which represents unimodality constraints per dimension. 1 indicates that function first decreases then increases, -1 indicates that function first increases then decreases, 0 indicates no unimodality constraints. |
| `edgeworth_trusts` | None or iterable of three-element tuples. First element is the index of the main (monotonic) feature. Second element is the index of the conditional feature. Third element is the direction of trust: 1 if higher values of the conditional feature should increase trust in the main feature and -1 otherwise. |
| `trapezoid_trusts` | None or iterable of three-element tuples. First element is the index of the main (monotonic) feature. Second element is the index of the conditional feature. Third element is the direction of trust: 1 if higher values of the conditional feature should increase trust in the main feature and -1 otherwise. |
| `monotonic_dominances` | None or iterable of two-element tuples. First element is the index of the dominant feature. Second element is the index of the weak feature. |
| `range_dominances` | None or iterable of two-element tuples. First element is the index of the dominant feature. Second element is the index of the weak feature. |
| `joint_monotonicities` | None or iterable of two-element tuples. Each tuple represents a pair of feature indices that require joint monotoniticity. |
| `joint_unimodalities` | None or tuple or iterable of tuples. Each tuple represents indices of single group of jointly unimodal features followed by 'valley' or 'peak'. |
| `num_iterations` | number of iterations of Dykstra's algorithm. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Projected weights tensor of same shape as `weights`. ||

<br />