IMTL-G

class torchjd.aggregation.IMTLG

GramianWeightedAggregator generalizing the method described in Towards Impartial Multi-task Learning. This generalization, defined formally in Jacobian Descent For Multi-Objective Optimization, supports matrices with some linearly dependent rows.

__call__(*args, **kwargs)

Computes the aggregation from the input matrix and applies all registered hooks.

Parameters:

matrix – The Jacobian to aggregate.

Return type:

Any

class torchjd.aggregation.IMTLGWeighting

Weighting [PSDMatrix] giving the weights of IMTLG.

__call__(*args, **kwargs)

Computes the vector of weights from the input Gramian and applies all registered hooks.

Parameters:

gramian – The Gramian from which the weights must be extracted.

Return type:

Any