paper-with-me

Papers

Maximum Entropy Auto-Encoding

2021-04-13 · Paul M Baggenstoss

In this paper, it is shown that an auto-encoder using optimal reconstruction significantly outperforms a conventional auto-encoder. Optimal reconstruction uses the conditional mean of the input given the features, under a maximum entropy prior distribution. The optimal reconstruction network, which is called deterministic projected belied network (D-PBN), resembles a standard reconstruction network, but with special non-linearities that mist be iteratively solved. The method, which can be seen as a generalization of maximum entropy image reconstruction, extends to multiple layers. In experiments, mean square reconstruction error reduced by up to a factor of two. The performance improvement diminishes for deeper networks, or for input data with unconstrained values (Gaussian assumption).

📄 PDF Abstract BibTeX arXiv:2104.07448

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

Matrix Information Theory for Self-Supervised Learning

2023-05-27 · Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang 외

The maximum entropy encoding framework provides a unified perspective for many non-contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this framework, we introduce Matrix-SSL, a novel approach t…

Contrastive LearningGSM8KLanguage ModelingLanguage Modelling+4

Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression

2021-05-05 · ICLR 2022 4 · Baeseong Park, Se Jung Kwon, Daehwan Oh, Byeongwook Kim 외

Even though fine-grained pruning techniques achieve a high compression ratio, conventional sparsity representations (such as CSR) associated with irregular sparsity degrade parallelism significantly. Practical pruning me…

Model Compression

A Scheme for Molecular Computation of Maximum Likelihood Estimators for Log-Linear Models

2015-06-10 · Manoj Gopalkrishnan

We propose a novel molecular computing scheme for statistical inference. We focus on the much-studied statistical inference problem of computing maximum likelihood estimators for log-linear models. Our scheme takes log-l…

MIM: Mutual Information Machine

2019-10-08 · Micha Livne, Kevin Swersky, David J. Fleet

We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encoura…

ClusteringDecoder

Efficient Learned Image Compression without Entropy Coding

2026-05-22 · Hao Cao, Wenqi Guo, Zhijin Qin, Jungong Han arxiv

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overc…

Image Compression