Search Results for author:
Found 3 papers, 1 papers with code
Provably Fair Representations
These provable properties can be used in a governance model involving a data producer, a data user and a data regulator, where there is a separation of concerns between fairness and target task utility to ensure transparency and prevent perverse incentives.
Risk Bounds for Transferring Representations With and Without Fine-Tuning
If the representation learned from the source task is fixed, we identify conditions on how the tasks relate to obtain an upper bound on target task risk via a VC dimension-based argument.
A Modular Theory of Feature Learning
We propose the idea of a risk gap induced by representation learning for a given prediction context, which measures the difference in the risk of some learner using the learned features as compared to the original inputs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
