no code implementations • 24 Jan 2024 • Anmol Kagrecha, Henrik Marklund, Benjamin Van Roy, Hong Jun Jeon, Richard Zeckhauser
Common crowdsourcing systems average estimates of a latent quantity of interest provided by many crowdworkers to produce a group estimate.
no code implementations • 23 Aug 2023 • Saurabh Kumar, Henrik Marklund, Benjamin Van Roy
In this paper, we propose L2 Init, a simple approach for maintaining plasticity by incorporating in the loss function L2 regularization toward initial parameters.
no code implementations • 10 Jul 2023 • Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy
The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning.
1 code implementation • ICLR 2022 • Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang
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.
6 code implementations • 14 Dec 2020 • Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton A. Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang
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.
no code implementations • 28 Sep 2020 • Marvin Mengxin Zhang, Henrik Marklund, Nikita Dhawan, Abhishek Gupta, Sergey Levine, Chelsea Finn
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
3 code implementations • NeurIPS 2021 • Marvin Zhang, Henrik Marklund, Nikita Dhawan, Abhishek Gupta, Sergey Levine, Chelsea Finn
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
12 code implementations • 21 Jan 2019 • Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, Jayne Seekins, David A. Mong, Safwan S. Halabi, Jesse K. Sandberg, Ricky Jones, David B. Larson, Curtis P. Langlotz, Bhavik N. Patel, Matthew P. Lungren, Andrew Y. Ng
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