- TrainSum.variational(*, decomposition: T, ncores: int = 2, nsweeps: int = 1, optimizer: Literal['optimal', 'dp', 'greedy', 'random-greedy', 'random-greedy-128', 'branch-all', 'branch-2', 'auto', 'auto-hq'] = DEFAULT_OPTIMIZER) VariationalOptions[T]
- TrainSum.variational(*, max_rank: int, cutoff: float = 0.0, ncores: int = 2, nsweeps: int = 1, optimizer: Literal['optimal', 'dp', 'greedy', 'random-greedy', 'random-greedy-128', 'branch-all', 'branch-2', 'auto', 'auto-hq'] = DEFAULT_OPTIMIZER) VariationalOptions[SVDecomposition[NDArray]]
Variational einsum operations. One can provide either a decomposition object or paramters for a singular value decomposition (max_rank, cutoff). ncores and nsweeps specify the sweeping strategy.
- Parameters:
max_rank (int)
cutoff (float)
decomposition (Any | None)
ncores (int)
nsweeps (int)
optimizer (Literal['optimal', 'dp', 'greedy', 'random-greedy', 'random-greedy-128', 'branch-all', 'branch-2', 'auto', 'auto-hq'])
- Return type: