SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.03687 · ICLR · 2021

WHEN OPTIMIZING f -DIVERGENCE IS ROBUST WITH LABEL NOISE

Yang Liu, Jiaheng Wei

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We show when maximizing a properly defined f -divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise. Leveraging its variational form, we derive a nice decoupling property for a family of f -divergence measures when label noise presents, where the divergence is shown to be a linear combination of the variational difference defined on the clean distribution and a bias term introduced due to the noise. The above derivation helps us analyze the robustness of different f -divergence functions. With established robustness, this family of f -divergence functions arises as useful metrics for the problem of learning with noisy labels, which do not require the specification of the labels' noise rate. When they are possibly not robust, we propose fixes to make them so. In addition to the analytical results, we present thorough experimental evidence. Our code is available at https: //github.com/UCSC-REAL/Robust-f-divergence-measures.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2011.03687")
get_code_for_paper("2011.03687")
have("2011.03687")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2011.03687.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2011.03687.svg)](https://syntology.ai/paper/2011.03687)

Connect an agent — have() is free.