Aarti Singh

Noise-Adaptive Margin-Based Active Learning and Lower Bounds under Tsybakov Noise Condition

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a simple noise-robust margin-based active learn-ing algorithm to find homogeneous (passing the origin) linearseparators and analyze its error convergence when labels arecorrupted by noise. We show that when the imposed noisesatisfies the Tsybakov …

KQML Based Communication Protocol for Multi Agent Systems

2015

The premise of this paper is to design a communication protocol for the agents operating in different multiagent systems. The protocol thus proposed offers full autonomy to agents for deciding if they are interested in …

Noise-Tolerant Interactive Learning from Pairwise Comparisons

2017 · arXiv (Cornell University)

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. …