paper-with-me

Papers

Efficient Maximal Coding Rate Reduction by Variational Forms

2022-03-31 · CVPR 2022 1 · Christina Baek, Ziyang Wu, Kwan Ho Ryan Chan, Tianjiao Ding, Yi Ma, Benjamin D. Haeffele

The principle of Maximal Coding Rate Reduction (MCR$^2$) has recently been proposed as a training objective for learning discriminative low-dimensional structures intrinsic to high-dimensional data to allow for more robust training than standard approaches, such as cross-entropy minimization. However, despite the advantages that have been shown for MCR$^2$ training, MCR$^2$ suffers from a significant computational cost due to the need to evaluate and differentiate a significant number of log-determinant terms that grows linearly with the number of classes. By taking advantage of variational forms of spectral functions of a matrix, we reformulate the MCR$^2$ objective to a form that can scale significantly without compromising training accuracy. Experiments in image classification demonstrate that our proposed formulation results in a significant speed up over optimizing the original MCR$^2$ objective directly and often results in higher quality learned representations. Further, our approach may be of independent interest in other models that require computation of log-determinant forms, such as in system identification or normalizing flow models.

📄 PDF Abstract BibTeX arXiv:2204.00077

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Federated Representation Learning via Maximal Coding Rate Reduction

2022-10-01 · Juan Cervino, Navid Naderializadeh, Alejandro Ribeiro

We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients. In particular, we move away from the commonly-used cross-entropy loss in federated lea…

Federated LearningRepresentation Learning

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

2020-06-15 · NeurIPS 2020 12 · Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song 외

To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measur…

ClusteringContrastive LearningImage Clustering

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

2024-12-23 · Ziyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai 외

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often im…

Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering

2024-12-25 · W. He, Z. Huang, X. Meng, X. Qi 외

In the era of pre-trained models, image clustering task is usually addressed by two relevant stages: a) to produce features from pre-trained vision models; and b) to find clusters from the pre-trained features. However, …

ClusteringImage Clustering

A Global Geometric Analysis of Maximal Coding Rate Reduction

2024-06-04 · Peng Wang, Huikang Liu, Druv Pai, Yaodong Yu 외

The maximal coding rate reduction (MCR$^2$) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in the derivation of fully explainable and…