Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression

Bibas, Koby; Feder, Meir

doi:10.48550/arxiv.2102.07181

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that, in this work, we extended the individual setting of [30] and allowed the usage of some prior w(θ) over the parameter space, which may be useful for regularization purposes. The learning problem is defined as the log-loss difference between a learner q and the reference learner (genie):…”

Section: The Individual Data Settingmentioning

confidence: 99%

Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks

Shayovitz,

Bibas,

Feder

2024

Entropy

View full text Add to dashboard Cite

Active learning (AL) is a paradigm focused on purposefully selecting training data to enhance a model’s performance by minimizing the need for annotated samples. Typically, strategies assume that the training pool shares the same distribution as the test set, which is not always valid in privacy-sensitive applications where annotating user data is challenging. In this study, we operate within an individual setting and leverage an active learning criterion which selects data points for labeling based on minimizing the min-max regret on a small unlabeled test set sample. Our key contribution lies in the development of an efficient algorithm, addressing the challenging computational complexity associated with approximating this criterion for neural networks. Notably, our results show that, especially in the presence of out-of-distribution data, the proposed algorithm substantially reduces the required training set size by up to 15.4%, 11%, and 35.1% for CIFAR10, EMNIST, and MNIST datasets, respectively.

show abstract

Section: The Individual Data Settingmentioning

confidence: 99%

Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks

Shayovitz,

Bibas,

Feder

2024

Entropy

View full text Add to dashboard Cite

show abstract

“…(2) We propose a general multitask-learning (MTL) [9] framework to incorporate collaborative information in the form of latent item representations into existing single-task content understanding models. (3) We explore several alternative approaches to combining collaborative information in the training procedure of image classification models.…”

mentioning

confidence: 99%

Collaborative Image Understanding

Bibas

Shalom²,

Jannach

2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Automatically understanding the contents of an image is a highly relevant problem in practice. In e-commerce and social media settings, for example, a common problem is to automatically categorize user-provided pictures. Nowadays, a standard approach is to fine-tune pre-trained image models with application-specific data. Besides images, organizations however often also collect collaborative signals in the context of their application, in particular how users interacted with the provided online content, e.g., in forms of viewing, rating, or tagging. Such signals are commonly used for item recommendation, typically by deriving latent user and item representations from the data. In this work, we show that such collaborative information can be leveraged to improve the classification process of new images. Specifically, we propose a multitask learning framework, where the auxiliary task is to reconstruct collaborative latent item representations. A series of experiments on datasets from e-commerce and social media demonstrates that considering collaborative signals helps to significantly improve the performance of the main task of image classification by up to 9.1%.

show abstract

Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression

Cited by 2 publications

References 0 publications

Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks

Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks

Collaborative Image Understanding

Contact Info

Product

Resources

About