Africa
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
The increasing reliance on ML models in high-stakes tasks has raised a major concern about fairness violations.
Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory
Hypothesis (L TH): a randomly-initialized dense neural network contains an extremely sparse subnet-work (i.e., a winning lottery ticket) such that, when trained from scratch with weights being reset to its initialization, can achieve similar performance to the original dense network within similar
ATD: Augmenting CP Tensor Decomposition by Self Supervision
Existing tensor decomposition objectives (e.g., Frobenius norm) are designed for fitting raw data under
Appendix
Figure 9: Example showing how a single line of HTML code is rendered by a browser's renderer.
The BigScience ROOTS Corpus: A1.6TB Composite Multilingual Dataset
As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings.
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
Our result demonstrates that multitask representation learning is provably more sample-efficient than learning each task individually, as long as the total number of tasks is above a certain threshold.