Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Compositional Risk Minimization
Divyat Mahajan, Mohammad Pezeshki, Charles Arnal +3
Compositional generalization is a crucial step towards developing data-efficient intelligent machines that generalize in human-like ways. In this work, we tackle a challenging form…
cs.LG2024
DRoP: Distributionally Robust Data Pruning
Artem Vysogorets, Kartik Ahuja, Julia Kempe
In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning. Data pruning offers a solution…
cs.LG2024
On Provable Length and Compositional Generalization
Kartik Ahuja, Amin Mansouri
Out-of-distribution generalization capabilities of sequence-to-sequence models can be studied from the lens of two crucial forms of generalization: length generalization -- the abi…