Contents Menu Expand Light mode Dark mode Auto light/dark mode
TorchJD
Light Logo Dark Logo

Getting Started

  • Installation
  • Examples
    • Basic Usage
    • Instance-Wise Risk Minimization (IWRM)
    • Partial Jacobian Descent for IWRM
    • Multi-Task Learning (MTL)
    • Instance-Wise Multi-Task Learning (IWMTL)
    • Recurrent Neural Network (RNN)
    • Monitoring aggregations
    • PyTorch Lightning Integration
    • Automatic Mixed Precision (AMP)

API Reference

  • autogram
    • Engine
  • autojac
    • backward
    • mtl_backward
  • aggregation
    • UPGrad
    • Aligned-MTL
    • CAGrad
    • ConFIG
    • Constant
    • DualProj
    • Flattening
    • GradDrop
    • IMTL-G
    • Krum
    • Mean
    • MGDA
    • Nash-MTL
    • PCGrad
    • Random
    • Sum
    • Trimmed Mean
Back to top

Random¶

class torchjd.aggregation.Random[source]¶

Aggregator that computes a random combination of the rows of the provided matrices, as defined in algorithm 2 of Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning.

class torchjd.aggregation.RandomWeighting[source]¶

Weighting that generates positive random weights at each call.

Next
Sum
Previous
PCGrad
Copyright © Valerian Rey, Pierre Quinton
Made with Sphinx and @pradyunsg's Furo