boundlab.expr.Cat#

class boundlab.expr.Cat[source]#

Bases: Expr

Expression for concatenating child expressions along a dimension.

The backward pass produces an embed LinearOp per child that zero-pads the child’s contribution into the full cat output shape. The VJP of F.pad (narrow) is computed automatically.

Methods

`__init__`
`backward`	Propagate weights to each child via zero-padding embed ops.
`bound_width`	Compute the width of the bounds for this expression.
`center`	Compute the center of the bounds for this expression.
`diag`
`expand`
`flatten`
`flip`
`gather`
`get_const`	Return the concrete tensor if self is a pure constant expression, else None.
`jacobian_ops_`	Recursively compute Jacobian ops for affine expressions.
`lb`	Compute a lower bound for this expression.
`narrow`
`permute`
`repeat`
`reshape`
`roll`
`scatter`
`squeeze`
`tile`
`to_string`	Return string representation with child strings substituted.
`transpose`
`ub`	Compute an upper bound for this expression.
`ublb`	Compute both an upper bound and a lower bound for this expression.
`unflatten`
`unsqueeze`
`with_children`	Return a new expression with the same type and flags but new children.
`zeros_set`

__init__(*children, dim=0)[source]#

property shape: torch.Size#: The shape of the output(s) produced by this expression.

property children: tuple[Expr, ...]#: The child expressions that serve as inputs to this expression.

with_children(*new_children)[source]#

Return a new expression with the same type and flags but new children.

backward(weights, direction='==')[source]#

Propagate weights to each child via zero-padding embed ops.

Parameters:

weights – A EinsumOp accumulated weight.
direction (Literal['>=', '<=', '==']) – Unused (Cat is always linear).

Returns:

(0, [child_weight_0, child_weight_1, ...])

to_string(*children_str)[source]#

Return string representation with child strings substituted.

property T: Expr#: Convenience for transpose of the last two dimensions.

__add__(other)#

__mul__(other)#: Element-wise multiplication (no broadcast).

bound_width()#

Compute the width of the bounds for this expression.

center()#

Compute the center of the bounds for this expression.

diag(diagonal=0)#

expand(*sizes)#

flatten(start_dim=0, end_dim=-1)#

flip(dims)#

gather(indices)#

get_const()#

Return the concrete tensor if self is a pure constant expression, else None.

Works for ConstVal and any AffineSum that has no symbolic children.

jacobian_ops_()#: Recursively compute Jacobian ops for affine expressions.

lb()#

Compute a lower bound for this expression.

narrow(dim, start, length)#

permute(*dims)#

repeat(*sizes)#

reshape(*shape)#

roll(shifts, dims)#

scatter(indices, output_shape)#

squeeze(dim=None)#

tile(*sizes)#

transpose(dim0, dim1)#

ub()#

Compute an upper bound for this expression.

ublb()#

Compute both an upper bound and a lower bound for this expression.

unflatten(dim, sizes)#

unsqueeze(dim)#

zeros_set(output_shape)#

id: int#: Unique identifier for the expression, used for topological sorting.

flags: ExprFlags#: Flags indicating expression properties for optimization.