Efficient Online Set-valued Classification with Bandit Feedback
- URL: http://arxiv.org/abs/2405.04393v1
- Date: Tue, 7 May 2024 15:14:51 GMT
- Title: Efficient Online Set-valued Classification with Bandit Feedback
- Authors: Zhou Wang, Xingye Qiao,
- Abstract summary: We propose Bandit Class-specific Conformal Prediction (BCCP), offering coverage guarantees on a class-specific granularity.
BCCP overcomes the challenges of sparsely labeled data in each iteration and generalizes the reliability and applicability of conformal prediction to online decision-making environments.
- Score: 10.882001129426726
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Conformal prediction is a distribution-free method that wraps a given machine learning model and returns a set of plausible labels that contain the true label with a prescribed coverage rate. In practice, the empirical coverage achieved highly relies on fully observed label information from data both in the training phase for model fitting and the calibration phase for quantile estimation. This dependency poses a challenge in the context of online learning with bandit feedback, where a learner only has access to the correctness of actions (i.e., pulled an arm) but not the full information of the true label. In particular, when the pulled arm is incorrect, the learner only knows that the pulled one is not the true class label, but does not know which label is true. Additionally, bandit feedback further results in a smaller labeled dataset for calibration, limited to instances with correct actions, thereby affecting the accuracy of quantile estimation. To address these limitations, we propose Bandit Class-specific Conformal Prediction (BCCP), offering coverage guarantees on a class-specific granularity. Using an unbiased estimation of an estimand involving the true label, BCCP trains the model and makes set-valued inferences through stochastic gradient descent. Our approach overcomes the challenges of sparsely labeled data in each iteration and generalizes the reliability and applicability of conformal prediction to online decision-making environments.
Related papers
- OTTER: Improving Zero-Shot Classification via Optimal Transport [13.789436156370893]
We introduce a simple and lightweight approach to adjust pretrained model predictions via optimal transport.
We validate our method in a wide array of zero-shot image and text classification tasks, improving accuracy by 4.8% and 15.9% on average.
arXiv Detail & Related papers (2024-04-12T13:18:47Z) - Model Calibration in Dense Classification with Adaptive Label
Perturbation [44.62722402349157]
Existing dense binary classification models are prone to being over-confident.
We propose Adaptive Label Perturbation (ASLP) which learns a unique label perturbation level for each training image.
ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data.
arXiv Detail & Related papers (2023-07-25T14:40:11Z) - Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and
Uncurated Unlabeled Data [70.25049762295193]
We introduce a novel conditional image generation framework that accepts noisy-labeled and uncurated data during training.
We propose soft curriculum learning, which assigns instance-wise weights for adversarial training while assigning new labels for unlabeled data.
Our experiments show that our approach outperforms existing semi-supervised and label-noise robust methods in terms of both quantitative and qualitative performance.
arXiv Detail & Related papers (2023-07-17T08:31:59Z) - Partial-Label Regression [54.74984751371617]
Partial-label learning is a weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels.
Previous studies on partial-label learning only focused on the classification setting where candidate labels are all discrete.
In this paper, we provide the first attempt to investigate partial-label regression, where each training example is annotated with a set of real-valued candidate labels.
arXiv Detail & Related papers (2023-06-15T09:02:24Z) - Label Inference Attack against Split Learning under Regression Setting [24.287752556622312]
We study the leakage in the scenario of the regression model, where the private labels are continuous numbers.
We propose a novel learning-based attack that integrates gradient information and extra learning regularization objectives.
arXiv Detail & Related papers (2023-01-18T03:17:24Z) - Dist-PU: Positive-Unlabeled Learning from a Label Distribution
Perspective [89.5370481649529]
We propose a label distribution perspective for PU learning in this paper.
Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions.
Experiments on three benchmark datasets validate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-12-06T07:38:29Z) - FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning [46.95063831057502]
We propose emphFreeMatch to define and adjust the confidence threshold in a self-adaptive manner according to the model's learning status.
FreeMatch achieves textbf5.78%, textbf13.59%, and textbf1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class.
arXiv Detail & Related papers (2022-05-15T10:07:52Z) - Learning with Proper Partial Labels [87.65718705642819]
Partial-label learning is a kind of weakly-supervised learning with inexact labels.
We show that this proper partial-label learning framework includes many previous partial-label learning settings.
We then derive a unified unbiased estimator of the classification risk.
arXiv Detail & Related papers (2021-12-23T01:37:03Z) - RATT: Leveraging Unlabeled Data to Guarantee Generalization [96.08979093738024]
We introduce a method that leverages unlabeled data to produce generalization bounds.
We prove that our bound is valid for 0-1 empirical risk minimization.
This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable.
arXiv Detail & Related papers (2021-05-01T17:05:29Z) - Distribution-free uncertainty quantification for classification under
label shift [105.27463615756733]
We focus on uncertainty quantification (UQ) for classification problems via two avenues.
We first argue that label shift hurts UQ, by showing degradation in coverage and calibration.
We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance.
arXiv Detail & Related papers (2021-03-04T20:51:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.