paper-with-me

Papers

Posterior Probability Matters: Doubly-Adaptive Calibration for Neural Predictions in Online Advertising

2022-05-15 · Penghui Wei, Weimin Zhang, Ruijie Hou, Jinquan Liu, Shaoguo Liu, Liang Wang, Bo Zheng

Predicting user response probabilities is vital for ad ranking and bidding. We hope that predictive models can produce accurate probabilistic predictions that reflect true likelihoods. Calibration techniques aim to post-process model predictions to posterior probabilities. Field-level calibration -- which performs calibration w.r.t. to a specific field value -- is fine-grained and more practical. In this paper we propose a doubly-adaptive approach AdaCalib. It learns an isotonic function family to calibrate model predictions with the guidance of posterior statistics, and field-adaptive mechanisms are designed to ensure that the posterior is appropriate for the field value to be calibrated. Experiments verify that AdaCalib achieves significant improvement on calibration performance. It has been deployed online and beats previous approach.

📄 PDF Abstract BibTeX arXiv:2205.07295

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Consistency Analysis for the Doubly Stochastic Dirichlet Process

2016-05-24 · Xing Sun, Nelson H. C. Yung, Edmund Y. Lam, Hayden K. -H. So

This technical report proves components consistency for the Doubly Stochastic Dirichlet Process with exponential convergence of posterior probability. We also present the fundamental properties for DSDP as well as infere…

Calibrating Where It Matters: Constrained Temperature Scaling

2024-06-17 · Stephen McKenna, Jacob Carse

We consider calibration of convolutional classifiers for diagnostic decision making. Clinical decision makers can use calibrated classifiers to minimise expected costs given their own cost function. Such functions are us…

Decision MakingDiagnostic

A Multi-armed Bandit MCMC, with applications in sampling from doubly intractable posterior

2019-03-13 · Guanyang Wang

Markov chain Monte Carlo (MCMC) algorithms are widely used to sample from complicated distributions, especially to sample from the posterior distribution in Bayesian inference. However, MCMC is not directly applicable wh…

Bayesian Inference

Posterior Calibrated Training on Sentence Classification Tasks

2020-04-29 · ACL 2020 6 · Taehee Jung, Dongyeop Kang, Hua Cheng, Lucas Mentch 외

Most classification models work by first predicting a posterior probability distribution over all classes and then selecting that class with the largest estimated probability. In many settings however, the quality of pos…

ClassificationGeneral ClassificationSentenceSentence Classification

Design-marginal calibration of Gaussian process predictive distributions: Bayesian and conformal approaches

2025-12-05 · Aurélien Pion, Emmanuel Vazquez arxiv

We study the calibration of Gaussian process (GP) predictive distributions in the interpolation setting from a design-marginal perspective. Conditioning on the data and averaging over a design measure μ, we formalize μ-c…