paper-with-me

홈 › Papers

Tighter bounds lead to improved classifiers

2016-06-29 · Nicolas Le Roux

The standard approach to supervised classification involves the minimization of a log-loss as an upper bound to the classification error. While this is a tight bound early on in the optimization, it overemphasizes the influence of incorrectly classified examples far from the decision boundary. Updating the upper bound during the optimization leads to improved classification rates while transforming the learning into a sequence of minimization problems. In addition, in the context where the classifier is part of a larger system, this modification makes it possible to link the performance of the classifier to that of the whole system, allowing the seamless introduction of external constraints.

📄 PDF Abstract BibTeX arXiv:1606.09202

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Tight lower bounds for Dynamic Time Warping

2021-02-14 · Geoffrey I. Webb, Francois Petitjean

Dynamic Time Warping (DTW) is a popular similarity measure for aligning and comparing time series. Due to DTW's high computation time, lower bounds are often employed to screen poor matches. Many alternative lower bounds…

Computational EfficiencyDynamic Time WarpingTime SeriesTime Series Analysis

Improved Margin Generalization Bounds for Voting Classifiers

2025-02-23 · Mikael Møller Høgsgaard, Kasper Green Larsen

In this paper we establish a new margin-based generalization bound for voting classifiers, refining existing results and yielding tighter generalization guarantees for widely used boosting algorithms such as AdaBoost (Fr…

Generalization Bounds

Tighter Bounds for Structured Estimation

2008-12-01 · NeurIPS 2008 12 · Olivier Chapelle, Chuong B. Do, Choon H. Teo, Quoc V. Le 외

Large-margin structured estimation methods work by minimizing a convex upper bound of loss functions. While they allow for efficient optimization algorithms, these convex formulations are not tight and sacrifice the abil…

Binary ClassificationGeneral ClassificationStructured Prediction

Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces

2021-03-24 · ICLR 2021 1 · Jack Prescott, Xiao Zhang, David Evans

Concentration of measure has been argued to be the fundamental cause of adversarial vulnerability. Mahloujifar et al. presented an empirical way to measure the concentration of a data distribution using samples, and empl…

Improved Training of Certifiably Robust Models

2019-09-25 · Chen Zhu, Renkun Ni, Ping-Yeh Chiang, Hengduo Li 외

Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical (PGD) robustness. In principle, relaxati…