Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
Nov 28, 2022
Speakers
About
Classification with rejection (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify. Though previous methods for CwR have been provided with theoretical guarantees, they are only compatible with certain loss functions, making them not flexible enough when the loss needs to be changed with the dataset in practice. In this paper, we derive a novel formulation for CwR that can be equipped with arbitrary loss functions while maintaining the theoretical guarantees. First, we show that K-class CwR is equivalent to a (K+1)-class classification problem on the original data distribution with an augmented class, and propose an empirical risk minimization formulation to solve this problem with an estimation error bound. Then, we find necessary and sufficient conditions for the learning consistency of the surrogates constructed on our proposed formulation equipped with any classification-calibrated multi-class losses, where consistency means the surrogate risk minimization implies the target risk minimization for CwR. Finally, experiments on benchmark datasets validate the effectiveness of our proposed method.Classification with rejection (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify. Though previous methods for CwR have been provided with theoretical guarantees, they are only compatible with certain loss functions, making them not flexible enough when the loss needs to be changed with the dataset in practice. In this paper, we derive a novel formulation for CwR that can be equipped with arbitrary loss functio…
Organizer
NeurIPS 2022
Account · 953 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Second-order Regression Model Shows Edge of Stability Behavior
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Distinct and Representative Modes for Image Captioning
Watch later
Qi Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal
Watch later
Yucheng Shi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Satlas: A Remote Sensing Dataset and Data Hub
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Riemannian Score-Based Generative Modeling
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Sampling from Log-Concave Distributions with Infinity-Distance Guarantees
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%