paper-with-me

홈 › Papers

Universally consistent predictive distributions

2017-08-06 · Vladimir Vovk

This paper describes simple universally consistent procedures of probability forecasting that satisfy a natural property of small-sample validity, under the assumption that the observations are produced independently in the IID fashion.

📄 PDF Abstract BibTeX arXiv:1708.01902

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Differentially-Private Bayes Consistency

2022-12-08 · Olivier Bousquet, Haim Kaplan, Aryeh Kontorovich, Yishay Mansour 외

We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP). We first handle the setting of binary classification and then extend our rule to the more general setting of density est…

Binary ClassificationDensity Estimation

Universally Consistent Online Learning with Arbitrarily Dependent Responses

2022-03-11 · Steve Hanneke

This work provides an online learning rule that is universally consistent under processes on (X,Y) pairs, under conditions only on the X process. As a special case, the conditions admit all processes on (X,Y) such that t…

Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

2020-02-12 · David Holzmüller, Ingo Steinwart

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically…

Vocal Bursts Valence Prediction

A partition-based similarity for classification distributions

2020-11-12 · Hayden S. Helm, Ronak D. Mehta, Brandon Duderstadt, Weiwei Yang 외

Herein we define a measure of similarity between classification distributions that is both principled from the perspective of statistical pattern recognition and useful from the perspective of machine learning practition…

ClassificationGeneral ClassificationSemantic SimilaritySemantic Textual Similarity

Predictive Uncertainty Quantification via Risk Decompositions for Strictly Proper Scoring Rules

2024-02-16 · Nikita Kotelevskii, Maxim Panov

Uncertainty quantification in predictive modeling often relies on ad hoc methods as there is no universally accepted formal framework for that. This paper introduces a theoretical approach to understanding uncertainty th…

Uncertainty Quantification