Fetching the paper…
Reading the bibliography…
It is well known that accurate probabilistic predictors can be trained through empirical risk minimisation with proper scoring rules as loss functions.
Should scoring rules be ’effective’?
Nau, R. F · 1985
Earlier work this paper cites.
Malinin, A., Chervontsev, S., Provilkov, I., and Gales, M. J. F · 2006
Earlier work this paper cites.
Strictly proper scoring rules, prediction, and estimation
Gneiting, T. and Raftery, A. E · 2007
Earlier work this paper cites.
Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertainty
Senge, R., Bösner, S., Dembczynski, K., Haasenritter, J., Hirsch, O., Donner-Banzhoff, N., and Hüllermeier, E · 2014
Earlier work this paper cites.
What uncertainties do we need in Bayesian deep learning for computer vision?
Kendall, A. and Gal, Y · 2017
Earlier work this paper cites.
Predictive uncertainty estimation via prior networks
Malinin, A. and Gales, M · 2018
Earlier work this paper cites.
Proper scoring rules and Bregman divergence
Ovcharov, E. Y · 2018
Earlier work this paper cites.
Evidential deep learning to quantify classification uncertainty
Sensoy, M., Kaplan, L., and Kandemir, M · 2018
Earlier work this paper cites.
Reverse KL-divergence training of prior networks: Improved uncertainty and adversarial robustness
Malinin, A. and Gales, M · 2019
Cited alongside, same era.
Deep evidential regression
Amini, A., Schwarting, W., Soleimany, A., and Rus, D · 2020
Cited alongside, same era.
Posterior network: Uncertainty estimation without OOD samples via density-based pseudo-counts
Charpentier, B., Zügner, D., and Günnemann, S · 2020
Cited alongside, same era.
Separation of aleatoric and epistemic uncertainty in deterministic deep neural networks
Huseljic, D., Sick, B., Herde, M., and Kottke, D · 2020
Cited alongside, same era.
Evidential deep learning for open set action recognition
Bao, W., Yu, Q., and Kong, Y · 2021
Cited alongside, same era.
Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods
Information aware max-norm Dirichlet networks for predictive uncertainty estimation
Tsiligkaridis, T · 2021
Later among the works it cites.
Pitfalls of epistemic uncertainty quantification through loss minimisation
Bengs, V., Hüllermeier, E., and Waegeman, W · 2022
Later among the works it cites.
Natural posterior network: Deep Bayesian predictive uncertainty for exponential family distributions
Charpentier, B., Borchert, O., Zugner, D., Geisler, S., and Günnemann, S · 2022
Later among the works it cites.
Predictive uncertainty quantification of deep neural networks using Dirichlet distributions
Hammam, A., Bonarens, F., Ghobadi, S. E., and Stiller, C · 2022
Later among the works it cites.
The unreasonable effectiveness of deep evidential regression
Meinert, N., Gawlikowski, J., and Lavin, A · 2022
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Hüllermeier, E. and Waegeman, W · 2021
Cited alongside, same era.
Evaluating robustness of predictive uncertainty estimation: Are Dirichlet-based models reliable?
Kopetzki, A., Charpentier, B., Zügner, D., Giri, S., and Günnemann, S · 2021
Cited alongside, same era.
Trustworthy multimodal regression with mixture of normal-inverse gamma distributions
Ma, H., Han, Z., Zhang, C., Fu, H., Zhou, J. T., and Hu, Q · 2021
Cited alongside, same era.
Ensemble distribution distillation
Malinin, A., Mlodozeniec, B., and Gales, M
Cited in the paper.
Improving evidential deep learning via multi-task learning
Oh, D. and Shin, B · 2022
Later among the works it cites.
Evidential conditional neural processes, 2022
Pandey, D. S. and Yu, Q · 2022
Later among the works it cites.