Robust Learning from Discriminative Feature Feedback

03/09/2020
by   Sanjoy Dasgupta, et al.
0

Recent work introduced the model of learning from discriminative feature feedback, in which a human annotator not only provides labels of instances, but also identifies discriminative features that highlight important differences between pairs of instances. It was shown that such feedback can be conducive to learning, and makes it possible to efficiently learn some concept classes that would otherwise be intractable. However, these results all relied upon perfect annotator feedback. In this paper, we introduce a more realistic, robust version of the framework, in which the annotator is allowed to make mistakes. We show how such errors can be handled algorithmically, in both an adversarial and a stochastic setting. In particular, we derive regret bounds in both settings that, as in the case of a perfect annotator, are independent of the number of features. We show that this result cannot be obtained by a naive reduction from the robust setting to the non-robust setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2022

Improved Robust Algorithms for Learning with Discriminative Feature Feedback

Discriminative Feature Feedback is a setting proposed by Dastupta et al....
research
10/13/2020

Regret minimization in stochastic non-convex learning via a proximal-gradient approach

Motivated by applications in machine learning and operations research, w...
research
02/27/2019

Adaptive Hedging under Delayed Feedback

The article is devoted to investigating the application of hedging strat...
research
10/12/2021

Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits

We consider a stochastic multi-armed bandit setting where feedback is li...
research
06/16/2022

Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback

The problem of online learning with graph feedback has been extensively ...
research
09/08/2021

Bilateral Trade: A Regret Minimization Perspective

Bilateral trade, a fundamental topic in economics, models the problem of...
research
06/30/2020

Provably More Efficient Q-Learning in the Full-Feedback/One-Sided-Feedback Settings

We propose two new Q-learning algorithms, Full-Q-Learning (FQL) and Elim...

Please sign up or login with your details

Forgot password? Click here to reset