paper-with-me

홈 › Papers

Towards Uncertainties in Deep Learning that Are Accurate and Calibrated

2021-09-29 · Volodymyr Kuleshov, Shachi Deshpande

Predictive uncertainties can be characterized by two properties---calibration and sharpness. This paper introduces algorithms that ensure the calibration of any model while maintaining sharpness. They apply in both classification and regression and guarantee the strong property of distribution calibration, while being simpler and more broadly applicable than previous methods (especially in the context of neural networks, which are often miscalibrated). Importantly, these algorithms achieve a long-standing statistical principle that forecasts should maximize sharpness subject to being fully calibrated. Using our algorithms, machine learning models can under some assumptions be calibrated without sacrificing accuracy: in a sense, calibration can be a free lunch. Empirically, we find that our methods improve predictive uncertainties on several tasks with minimal computational and implementation overhead.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learningregression

Similar Papers 제목 키워드 기반

Calibrated Model-Based Deep Reinforcement Learning

2019-06-19 · Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer 외

Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inacc…

Deep Reinforcement LearningmodelModel-based Reinforcement LearningMuJoCo+3

Calibrated Probabilistic Forecasts for Arbitrary Sequences

2024-09-27 · Charles Marx, Volodymyr Kuleshov, Stefano Ermon

Real-world data streams can change unpredictably due to distribution shifts, feedback loops and adversarial actors, which challenges the validity of forecasts. We present a forecasting framework ensuring valid uncertaint…

Decision Makingvalid

Calibrated Perception Uncertainty Across Objects and Regions in Bird's-Eye-View

2022-11-08 · Markus Kängsepp, Meelis Kull

In driving scenarios with poor visibility or occlusions, it is important that the autonomous vehicle would take into account all the uncertainties when making driving decisions, including choice of a safe speed. The grid…

Semantic Segmentation

Accurate Uncertainties for Deep Learning Using Calibrated Regression

2018-07-01 · ICML 2018 7 · Volodymyr Kuleshov, Nathan Fenner, Stefano Ermon

Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems. Bayesian methods provide a general framework to quantify uncertainty. However, because of model misspeci…

Deep LearningModel-based Reinforcement LearningregressionReinforcement Learning+4

Online Calibrated and Conformal Prediction Improves Bayesian Optimization

2021-12-08 · Shachi Deshpande, Charles Marx, Volodymyr Kuleshov

Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization. However, these estimates can be imperfect if the data violates assumptions made by the model (e.…

Bayesian OptimizationConformal PredictionDecision MakingHyperparameter Optimization+1