Results 11 to 20 of about 195,059 (253)
A recent survey on instance-dependent positive and unlabeled learning
Fundamental ResearchTraining with confident positive-labeled instances has received a lot of attention in Positive and Unlabeled (PU) learning tasks, and this is formally termed “Instance-Dependent PU learning”. In instance-dependent PU learning, whether a positive instance
Chen Gong +4 more
doaj +3 more sources
Instance-Dependent Partial Label Learning
CoRR, 2021 Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, this assumption is not realistic
Ning Xu 0009 +3 more
openaire +3 more sources
Instance-dependent cost-sensitive learning for detecting transfer fraud [PDF]
European Journal of Operational Research, 2022 24 pages, 4 figures ...
Höppner, Sebastiaan +3 more
openaire +6 more sources
An instance-dependent simulation framework for learning with label noise
Machine Learning, 2022 We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to independent and class-conditional random flipping.
Keren Gu +5 more
openaire +2 more sources
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning
J. Mach. Learn. Res., 2022 Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired a growing effort in obtaining instance-dependent guarantees and deriving instance-optimal algorithms for RL ...
Koulik Khamaru +3 more
openaire +4 more sources
A Second-Order Approach to Learning with Instance-Dependent Label Noise [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Learning with label noise.
Zhaowei Zhu +2 more
openaire +2 more sources
Learning from Binary Labels with Instance-Dependent Corruption [PDF]
CoRR, 2016 Suppose we have a sample of instances paired with binary labels corrupted by arbitrary instance- and label-dependent noise. With sufficiently many such samples, can we optimally classify and rank instances with respect to the noise-free distribution? We provide a theoretical analysis of this question, with three main contributions. First, we prove that
Aditya Krishna Menon +2 more
openaire +5 more sources
Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
SIAM Journal on Mathematics of Data Science, 2021 38 pages, 3 ...
Koulik Khamaru +4 more
openaire +2 more sources
Optimistic PAC Reinforcement Learning: the Instance-Dependent View
CoRR, 2022 Optimistic algorithms have been extensively studied for regret minimization in episodic tabular MDPs, both from a minimax and an instance-dependent view. However, for the PAC RL problem, where the goal is to identify a near-optimal policy with high probability, little is known about their instance-dependent sample complexity.
Tirinzoni, Andrea +2 more
openaire +5 more sources
Progressive Purification for Instance-Dependent Partial Label Learning
CoRR, 2022 Accepted to International Conference on Machine Learning 2023 (ICML 2023)
Ning Xu 0009 +4 more
openaire +3 more sources