paper-with-me

Papers

Efficient improper learning for online logistic regression

2020-03-18 · Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi

We consider the setting of online logistic regression and consider the regret with respect to the 2-ball of radius B. It is known (see [Hazan et al., 2014]) that any proper algorithm which has logarithmic regret in the number of samples (denoted n) necessarily suffers an exponential multiplicative constant in B. In this work, we design an efficient improper algorithm that avoids this exponential constant while preserving a logarithmic regret. Indeed, [Foster et al., 2018] showed that the lower bound does not apply to improper algorithms and proposed a strategy based on exponential weights with prohibitive computational complexity. Our new algorithm based on regularized empirical risk minimization with surrogate losses satisfies a regret scaling as O(B log(Bn)) with a per-round time-complexity of order O(d^2).

📄 PDF Abstract BibTeX arXiv:2003.08109

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

Logistic Regression: The Importance of Being Improper

2018-03-25 · Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri 외

Learning linear predictors with the logistic loss---both in stochastic and online settings---is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing "fas…

regression

Efficient Methods for Online Multiclass Logistic Regression

2021-10-06 · Naman Agarwal, Satyen Kale, Julian Zimmert

Multiclass logistic regression is a fundamental task in machine learning with applications in classification and boosting. Previous work (Foster et al., 2018) has highlighted the importance of improper predictors for ach…

regression

Localization, Convexity, and Star Aggregation

2021-05-19 · NeurIPS 2021 12 · Suhas Vijaykumar

Offset Rademacher complexities have been shown to provide tight upper bounds for the square loss in a broad class of problems including improper statistical learning and online learning. We show that the offset complexit…

High-Probability Risk Bounds via Sequential Predictors

2023-08-15 · Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi

Online learning methods yield sequential regret bounds under minimal assumptions and provide in-expectation risk bounds for statistical learning. However, despite the apparent advantage of online guarantees over their st…

Density Estimationregression

Meta Learning for High-dimensional Ising Model Selection Using $\ell_1$-regularized Logistic Regression

2022-08-19 · Huiming Xie, Jean Honorio

In this paper, we consider the meta learning problem for estimating the graphs associated with high-dimensional Ising models, using the method of $\ell_1$-regularized logistic regression for neighborhood selection of eac…

Meta-LearningModel Selectionregression