# Design and Analysis of Consistent Algorithms for Multiclass Learning Problems

@inproceedings{Harish2015DesignAA, title={Design and Analysis of Consistent Algorithms for Multiclass Learning Problems}, author={Guruprasad Ramaswami Harish}, year={2015} }

- Published 2015

We consider the broad framework of supervised learning, where one gets examples of objects together with some labels (such as tissue samples labeled as cancerous or noncancerous, or images of handwritten digits labeled with the correct digit in 0-9), and the goal is to learn a prediction model which given a new object, makes an accurate prediction. The notion of accuracy depends on the learning problem under study and is measured by a performance measure of interest. A supervised learning… CONTINUE READING

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 117 REFERENCES

## Learning Scoring Functions with Order-Preserving Losses and Standardized Supervision

VIEW 12 EXCERPTS

HIGHLY INFLUENTIAL

## On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines

VIEW 16 EXCERPTS

HIGHLY INFLUENTIAL

## Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization

VIEW 5 EXCERPTS

HIGHLY INFLUENTIAL

## Surrogate Regret Bounds for the Area Under the ROC Curve via Strongly Proper Losses

VIEW 9 EXCERPTS

HIGHLY INFLUENTIAL

## "On the (Non-)existence of Convex, Calibrated Surrogate Losses for Ranking"

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## On NDCG Consistency of Listwise Ranking Methods

VIEW 10 EXCERPTS

HIGHLY INFLUENTIAL

## On the Consistency of Ranking Algorithms

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## Aggregating inconsistent information: Ranking and clustering

VIEW 6 EXCERPTS

HIGHLY INFLUENTIAL

## Classification with a Reject Option using a Hinge Loss

VIEW 8 EXCERPTS

HIGHLY INFLUENTIAL

## Convexity, classification, and risk bounds

VIEW 6 EXCERPTS

HIGHLY INFLUENTIAL

#### Similar Papers

Loading similar papers…