Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Patel, Niket, Shwartz-Ziv, Ravid
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Information Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks
por: Zhang, Shihao, et al.
Publicado: (2025)

Information-Theoretic Generalization Bounds for Deep Neural Networks
por: He, Haiyun, et al.
Publicado: (2024)

Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors
por: Khorasani, Arian, et al.
Publicado: (2026)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
por: Shani, Chen, et al.
Publicado: (2025)

Application of Deep Learning in Biological Data Compression
por: Zou, Chunyu
Publicado: (2025)

Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance
por: Kim, Yuriy, et al.
Publicado: (2026)

AlphaZip: Neural Network-Enhanced Lossless Text Compression
por: Narashiman, Swathi Shree, et al.
Publicado: (2024)

Coding for Computation: Efficient Compression of Neural Networks for Reconfigurable Hardware
por: Rosenberger, Hans, et al.
Publicado: (2025)

Neural Polar Decoders for DNA Data Storage
por: Aharoni, Ziv, et al.
Publicado: (2025)

On the Local Complexity of Linear Regions in Deep ReLU Networks
por: Patel, Niket, et al.
Publicado: (2024)

Deep Generative Modeling Reshapes Compression and Transmission: From Efficiency to Resiliency
por: Dai, Jincheng, et al.
Publicado: (2024)

Quantum Neural Estimation of Entropies
por: Goldfeld, Ziv, et al.
Publicado: (2023)

Neural Polar Decoders for Deletion Channels
por: Aharoni, Ziv, et al.
Publicado: (2025)

Agnostic Sample Compression Schemes for Regression
por: Attias, Idan, et al.
Publicado: (2018)

Lossless and Near-Lossless Compression for Foundation Models
por: Hershcovitch, Moshik, et al.
Publicado: (2024)

ZipNN: Lossless Compression for AI Models
por: Hershcovitch, Moshik, et al.
Publicado: (2024)

Exploration-Exploitation Tradeoff in Universal Lossy Compression
por: Weinberger, Nir, et al.
Publicado: (2025)

Code Rate Optimization via Neural Polar Decoders
por: Aharoni, Ziv, et al.
Publicado: (2025)

Context Steering: A New Paradigm for Compression-based Embeddings by Synthesizing Relevant Information Features
por: Sarasa, Guillermo, et al.
Publicado: (2025)

Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
por: Lei, Eric, et al.
Publicado: (2024)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
por: Ayonrinde, Kola, et al.
Publicado: (2024)

Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
por: Phan, Buu, et al.
Publicado: (2025)

Fundamental Limits of CSI Compression in FDD Massive MIMO
por: Park, Bumsu, et al.
Publicado: (2026)

Information-Theoretic Limits of Quantum Learning via Data Compression
por: Angrisani, Armando, et al.
Publicado: (2021)

dreaMLearning: Data Compression Assisted Machine Learning
por: Zhao, Xiaobo, et al.
Publicado: (2025)

Performance Guarantees for Quantum Neural Estimation of Entropies
por: Sreekumar, Sreejith, et al.
Publicado: (2025)

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth
por: Kögler, Kevin, et al.
Publicado: (2024)

Data-dependent Generalization Bounds via Variable-Size Compressibility
por: Sefidgaran, Milad, et al.
Publicado: (2023)

On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
por: Salehkalaibar, Sadaf, et al.
Publicado: (2025)

Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
por: Samuelson, Jeremy J
Publicado: (2026)

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization
por: Shwartz-Ziv, Ravid, et al.
Publicado: (2023)

Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization
por: Borzechowski, Florian, et al.
Publicado: (2025)

Layer by Layer: Uncovering Hidden Representations in Language Models
por: Skean, Oscar, et al.
Publicado: (2025)

GO-GenZip: Goal-Oriented Generative Sampling and Hybrid Compression
por: Talli, Pietro, et al.
Publicado: (2026)

Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling
por: Nguyen, Nam, et al.
Publicado: (2026)

Quad Length Codes for Lossless Compression of e4m3
por: Agrawal, Aditya, et al.
Publicado: (2026)

Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
por: Kudo, Sota, et al.
Publicado: (2024)

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
por: Wang, Weiqi, et al.
Publicado: (2026)

Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks
por: Evans, Bethan, et al.
Publicado: (2026)

Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
por: Butakov, Ivan, et al.
Publicado: (2023)