Neural Ensemble Search for Performant and Calibrated Predictions

By Sheheryar Zaidi, Arber Zela, Thomas Elsken, Chris C. Holmes, Frank Hutter, Yee Whye Teh. 2020

41 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Sergey Levine
3. Dustin Tran
4. Jasper Snoek
5. Rodolphe Jenatton
6. Dacheng Tao
7. Florian Wenzel
8. Ruslan Salakhutdinov

Citations in the corpus

• BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019, neutral): “Ensembles of neural networks, even of size three and five, have been shown in some cases to give more reliable uncertainty estimates than other leading approaches such as BNNs (Lakshminarayanan, Pritzel, and Blundell 2017; Beluch et al. 2018; Choi et al. 2016; Snoek et al. 2019; Zaidi et al. 2020).”
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, methodology): “Moreover, neural ensemble search methods [489] are well-developed techniques for uncertainty calibration.”
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification (2020, methodology): “We vary the hyperparameters while keeping the architecture fixed while [75] study the converse.”