Wonjong Rhee, Jungwook Shin, Jaeill Kim, Suhyun Kang, Duhun Hwang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have been studied to improve the quality of representation. However, manipulating such properties can be challenging in terms of implementational effectiveness and general applicability. To address these limitations, we propose to regularize von Neumann entropy (VNE) of representation. First, we demonstrate that the mathematical formulation of VNE is superior in effectively manipulating the eigenvalues of the representation autocorrelation matrix. Then, we demonstrate that it is widely applicable in improving stateof-the-art algorithms or popular benchmark algorithms by investigating domain-generalization, meta-learning, selfsupervised learning, and generative models. In addition, we formally establish theoretical connections with rank, disentanglement, and isotropy of representation. Finally, we provide discussions on the dimension control of VNE and the relationship with Shannon entropy. Code is available at: https://github.com/jaeill/CVPR23-VNE.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.01434")
get_code_for_paper("2304.01434")
have("2304.01434")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.01434.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.01434)
Connect an agent — have() is free.