paper-with-me

홈 › Papers

Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems

2022-11-23 · Jirong Yi, Qiaosheng Zhang, Zhen Chen, Qiao Liu, Wei Shao, Yusen He, Yaohua Wang

As one of the central tasks in machine learning, regression finds lots of applications in different fields. An existing common practice for solving regression problems is the mean square error (MSE) minimization approach or its regularized variants which require prior knowledge about the models. Recently, Yi et al., proposed a mutual information based supervised learning framework where they introduced a label entropy regularization which does not require any prior knowledge. When applied to classification tasks and solved via a stochastic gradient descent (SGD) optimization algorithm, their approach achieved significant improvement over the commonly used cross entropy loss and its variants. However, they did not provide a theoretical convergence analysis of the SGD algorithm for the proposed formulation. Besides, applying the framework to regression tasks is nontrivial due to the potentially infinite support set of the label. In this paper, we investigate the regression under the mutual information based supervised learning framework. We first argue that the MSE minimization approach is equivalent to a conditional entropy learning problem, and then propose a mutual information learning formulation for solving regression problems by using a reparameterization technique. For the proposed formulation, we give the convergence analysis of the SGD algorithm for solving it in practice. Finally, we consider a multi-output regression data model where we derive the generalization performance lower bound in terms of the mutual information associated with the underlying data distribution. The result shows that the high dimensionality can be a bless instead of a curse, which is controlled by a threshold. We hope our work will serve as a good starting point for further research on the mutual information based regression.

📄 PDF Abstract BibTeX arXiv:2211.12685

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Entropy Regularization 설명 없음

Similar Papers 제목 키워드 기반

Regressor-Segmenter Mutual Prompt Learning for Crowd Counting

2023-12-04 · CVPR 2024 1 · Mingyue Guo, Li Yuan, Zhaoyi Yan, Binghui Chen 외

Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios, however, regressors are challenged by uncontrollable annotation variance, which causes …

Crowd CountingPrompt Learning

Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems

2022-09-21 · Jirong Yi, Qiaosheng Zhang, Zhen Chen, Qiao Liu 외

Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets. As a main-stream loss function, the cr…

Binary Classification

Balancing Application Relevant and Sparsity Revealing Excitation in Input Design

2024-02-08 · Javad Parsa, Cristian R. Rojas, Håkan Hjalmarsson

The maximum absolute correlation between regressors, which is called mutual coherence, plays an essential role in sparse estimation. A regressor matrix whose columns are highly correlated may result from optimal input de…

Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems

2022-10-03 · Jirong Yi, Qiaosheng Zhang, Zhen Chen, Qiao Liu 외

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can …

Binary ClassificationData Augmentation

Self-Supervised Representation Learning From Multi-Domain Data

2019-10-01 · ICCV 2019 10 · Zeyu Feng, Chang Xu, Dacheng Tao

We present an information-theoretically motivated constraint for self-supervised representation learning from multiple related domains. In contrast to previous self-supervised learning methods, our approach learns from m…

Representation LearningSelf-Supervised LearningTransfer Learning