# An Efficient Approximate Method for Online Convolutional Dictionary Learning

arXiv: https://arxiv.org/abs/2301.10583 · HTML: https://mlsanity.com/paper/2301.10583/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 26 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [Convolutional Dictionary Learning: A Comparative Review and New Algorithms](https://mlsanity.com/paper/1709.02893/) (2017)
- [Convolutional Dictionary Learning via Local Processing](https://mlsanity.com/paper/1705.03239/) (2017)
- [Scalable Online Convolutional Sparse Coding](https://mlsanity.com/paper/1706.06972/) (2017)
- [Efficient ADMM-based Algorithms for Convolutional Sparse Coding](https://mlsanity.com/paper/2109.02969/) (2021)

## Built on by (most cited first, 1 of 1)

- [Efficient Chambolle-Pock based algorithms for Convoltional sparse representation](https://mlsanity.com/paper/2508.02152/) (2025)

## Abstract (arXiv)

Most existing convolutional dictionary learning (CDL) algorithms are based on batch learning, where the dictionary filters and the convolutional sparse representations are optimized in an alternating manner using a training dataset. When large training datasets are used, batch CDL algorithms become prohibitively memory-intensive. An online-learning technique is used to reduce the memory requirements of CDL by optimizing the dictionary incrementally after finding the sparse representations of each training sample. Nevertheless, learning large dictionaries using the existing online CDL (OCDL) algorithms remains highly computationally expensive. In this paper, we present a novel approximate OCDL method that incorporates sparse decomposition of the training samples. The resulting optimization problems are addressed using the alternating direction method of multipliers. Extensive experimental evaluations using several image datasets show that the proposed method substantially reduces computational costs while preserving the effectiveness of the state-of-the-art OCDL algorithms.