Search Results for author:
Found 8 papers, 4 papers with code
Adaptive Crowdsourcing Via Self-Supervised Learning
Common crowdsourcing systems average estimates of a latent quantity of interest provided by many crowdworkers to produce a group estimate.
Maintaining Plasticity in Continual Learning via Regenerative Regularization
In this paper, we propose L2 Init, a simple approach for maintaining plasticity by incorporating in the loss function L2 regularization toward initial parameters.
Continual Learning as Computationally Constrained Reinforcement Learning
The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning.
Extending the WILDS Benchmark for Unsupervised Adaptation
Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well.
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild.
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
On a validation set of 200 chest radiographic studies which were manually annotated by 3 board-certified radiologists, we find that different uncertainty approaches are useful for different pathologies.
Ranked #95 on
Multi-Label Classification
on CheXpert
