← Back to papers
2019 COLT COLT 2019

Open Problem: How fast can a multiclass test set be overfit?

Abstract

We ask how many measurements of the accuracy on a multiclass benchmark are needed to achieve a given amount of overfitting.

❓ The Questioner
🐣 Hot Topic Early Bird — multiclass classification
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Vitaly Feldman , Roy Frostig , Moritz Hardt

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory

Keywords

learning theory benchmark evaluation multiclass classification test set
Download PDF

Related papers

Inference under Information Constraints: Lower Bounds from Chi-Square Contraction 2019
Learning in Non-convex Games with an Optimization Oracle 2019
Learning to Prune: Speeding up Repeated Computations 2019
A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise 2019
Learning Two Layer Rectified Neural Networks in Polynomial Time 2019