paper-with-me

홈 › Papers

Learning to Compress: Local Rank and Information Compression in Deep Neural Networks

2024-10-10 · Niket Patel, Ravid Shwartz-Ziv

Deep neural networks tend to exhibit a bias toward low-rank solutions during training, implicitly learning low-dimensional feature representations. This paper investigates how deep multilayer perceptrons (MLPs) encode these feature manifolds and connects this behavior to the Information Bottleneck (IB) theory. We introduce the concept of local rank as a measure of feature manifold dimensionality and demonstrate, both theoretically and empirically, that this rank decreases during the final phase of training. We argue that networks that reduce the rank of their learned representations also compress mutual information between inputs and intermediate layers. This work bridges the gap between feature manifold rank and information compression, offering new insights into the interplay between information bottlenecks and representation learning.

📄 PDF Abstract BibTeX arXiv:2410.07687

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Tensor Low-Rank Reconstruction for Semantic Segmentation

2020-08-02 · ECCV 2020 8 · Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He 외

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired c…

Semantic Segmentation

Layer-wise dynamic rank for compressing large language models

2025-09-30 · Zhendong Mi, Bian Sun, Grace Li Zhang, Shaoyi Huang arxiv

Large language models (LLMs) have rapidly scaled in size, bringing severe memory and computational challenges that hinder their deployment. Singular Value Decomposition (SVD)-based compression has emerged as an appealing…

SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

2026-02-03 · Xing Hu, Dawei Yang, Yuan Cheng, Zhixuan Chen 외 arxiv

The rapid growth in the parameter scale of large language models (LLMs) has created a high demand for efficient compression techniques. As a hardware-agnostic and highly compatible technique, low-rank compression has bee…

LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

2026-07-03 · Zhuowen Liu, Longkun Hao, Shiyu Feng, Xiaowen Chang 외 arxiv

The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and highly compatible approach, low-rank compression has be…

Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression

2026-04-02 · Ruoling Qi, Yirui Liu, Xuaner Wu, Xiangyu Wang 외 arxiv

The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-friendly solution to reduce these costs.…