paper-with-me

Papers

Margin-Independent Online Multiclass Learning via Convex Geometry

2021-11-15 · NeurIPS 2021 12 · Guru Guruganesh, Allen Liu, Jon Schneider, Joshua Wang

We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online. Unlike traditional bounds which seek to minimize the misclassification rate, we minimize the total distance from each query to the region corresponding to its correct label. When the true labels are determined via a nearest neighbor partition -- i.e. the label of a point is given by which of $k$ centers it is closest to in Euclidean distance -- we show that one can achieve a loss that is independent of the total number of queries. We complement this result by showing that learning general convex sets requires an almost linear loss per query. Our results build off of regret guarantees for the geometric problem of contextual search. In addition, we develop a novel reduction technique from multiclass classification to binary classification which may be of independent interest.

📄 PDF Abstract BibTeX arXiv:2111.08057

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationClassificationMulti-class Classification

Similar Papers 제목 키워드 기반

Convex Optimization for Binary Classifier Aggregation in Multiclass Problems

2014-01-16 · Sunho Park, TaeHyun Hwang, Seungjin Choi

Multiclass problems are often decomposed into multiple binary problems that are solved by individual binary classifiers whose results are integrated into a final answer. Various methods, including all-pairs (APs), one-ve…

Online Agnostic Multiclass Boosting

2022-05-30 · Vinod Raman, Ambuj Tewari

Boosting is a fundamental approach in machine learning that enjoys both strong theoretical and practical guarantees. At a high-level, boosting algorithms cleverly aggregate weak learners to generate predictions with arbi…

Binary Classification

A Unified Framework for Multiclass and Multilabel Support Vector Machines

2020-03-25 · Hoda Shajari, Anand Rangarajan

We propose a novel integrated formulation for multiclass and multilabel support vector machines (SVMs). A number of approaches have been proposed to extend the original binary SVM to an all-in-one multiclass SVM. However…

Online Multiclass Classification Based on Prediction Margin for Partial Feedback

2019-02-04 · Takuo Kaneko, Issei Sato, Masashi Sugiyama

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have bee…

ClassificationGeneral Classification

The price of bandit information in multiclass online classification

2013-02-05 · Amit Daniely, Tom Helbertal

We consider two scenarios of multiclass online learning of a hypothesis class $H\subseteq Y^X$. In the {\em full information} scenario, the learner is exposed to instances together with their labels. In the {\em bandit} …

ClassificationGeneral ClassificationOpen-Ended Question Answering