Image de couverture de livre

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kögler, Kevin, Shevchenko, Alexander, Hassani, Hamed, Mondelli, Marco
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
par: Lei, Eric, et autres
Publié: (2024)

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
par: Zhang, Yihan, et autres
Publié: (2024)

Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models
par: Zhang, Yihan, et autres
Publié: (2022)

Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
par: Zhang, Yihan, et autres
Publié: (2023)

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
par: Kovačević, Filip, et autres
Publié: (2025)

Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Coding
par: Lei, Eric, et autres
Publié: (2022)

Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff
par: Lei, Eric, et autres
Publié: (2025)

Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
par: Zhang, Yihan, et autres
Publié: (2026)

Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
par: Pour, Alireza F., et autres
Publié: (2023)

Attention with Trained Embeddings Provably Selects Important Tokens
par: Wu, Diyuan, et autres
Publié: (2025)

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
par: Moniri, Behrad, et autres
Publié: (2024)

Structured Superposition of Autoencoders for UEP Codes at Intermediate Blocklengths
par: Ninkovic, Vukan, et autres
Publié: (2025)

Transformers on Markov Data: Constant Depth Suffices
par: Rajaraman, Nived, et autres
Publié: (2024)

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders
par: Chen, Siyu, et autres
Publié: (2025)

Application of Deep Learning in Biological Data Compression
par: Zou, Chunyu
Publié: (2025)

Data-dependent Generalization Bounds via Variable-Size Compressibility
par: Sefidgaran, Milad, et autres
Publié: (2023)

Adversarial Jamming for Autoencoder Distribution Matching
par: El-Geresy, Waleed, et autres
Publié: (2025)

Provable tradeoffs in adversarially robust classification
par: Dobriban, Edgar, et autres
Publié: (2020)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
par: Hassani, Hamed, et autres
Publié: (2022)

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
par: Wang, Zixuan, et autres
Publié: (2024)

Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
par: Cheng, Yuan, et autres
Publié: (2025)

Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
par: Li, Gen, et autres
Publié: (2025)

MinGRU-Based Encoder for Turbo Autoencoder Frameworks
par: Fritschek, Rick, et autres
Publié: (2025)

Greedy Sampling Is Provably Efficient for RLHF
par: Wu, Di, et autres
Publié: (2025)

Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications
par: Seifert, Daniel, et autres
Publié: (2025)

Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
par: Barbier, Jean, et autres
Publié: (2024)

Learning to Compress: Local Rank and Information Compression in Deep Neural Networks
par: Patel, Niket, et autres
Publié: (2024)

Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective
par: Langer, Carlotta, et autres
Publié: (2024)

dreaMLearning: Data Compression Assisted Machine Learning
par: Zhao, Xiaobo, et autres
Publié: (2025)

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
par: Cai, Changxiao, et autres
Publié: (2026)

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
par: Pedrotti, Francesco, et autres
Publié: (2023)

Lossless and Near-Lossless Compression for Foundation Models
par: Hershcovitch, Moshik, et autres
Publié: (2024)

ZipNN: Lossless Compression for AI Models
par: Hershcovitch, Moshik, et autres
Publié: (2024)

Exploration-Exploitation Tradeoff in Universal Lossy Compression
par: Weinberger, Nir, et autres
Publié: (2025)

Agnostic Sample Compression Schemes for Regression
par: Attias, Idan, et autres
Publié: (2018)

Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
par: Yu, Wenrui, et autres
Publié: (2024)

Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
par: Phan, Buu, et autres
Publié: (2025)

Fundamental Limits of CSI Compression in FDD Massive MIMO
par: Park, Bumsu, et autres
Publié: (2026)

Compressed Sensor Caching and Collaborative Sparse Data Recovery with Anchor Alignment
par: Yang, Yi-Jen, et autres
Publié: (2024)

Efficient Learned Data Compression via Dual-Stream Feature Decoupling
par: Ma, Huidong, et autres
Publié: (2026)