Image de couverture de livre

Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kudo, Sota, Ono, Naoaki, Kanaya, Shigehiko, Huang, Ming
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
par: Wang, Weiqi, et autres
Publié: (2026)

Label Smoothing is a Pragmatic Information Bottleneck
par: Kudo, Sota
Publié: (2025)

Pre-training of Molecular GNNs via Conditional Boltzmann Generator
par: Koge, Daiki, et autres
Publié: (2023)

The Causal Information Bottleneck and Optimal Causal Variable Abstractions
par: Simoes, Francisco N. F. Q., et autres
Publié: (2024)

Interpret Gaussian Process Models by Using Integrated Gradients
par: Fan Zhang, et autres
Publié: (2024)

The Alignment Bottleneck
par: Cao, Wenjun
Publié: (2025)

Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
par: Federici, Marco, et autres
Publié: (2023)

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
par: Oomerjee, Adnan, et autres
Publié: (2025)

A Distance Metric Learning Model Based On Variational Information Bottleneck
par: Zhang, YaoDan, et autres
Publié: (2024)

Learning is Forgetting: LLM Training As Lossy Compression
par: Conklin, Henry C., et autres
Publié: (2026)

General Information Metrics for Improving AI Model Training Efficiency
par: Xu, Jianfeng, et autres
Publié: (2025)

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

Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks
par: Hu, Haoji, et autres
Publié: (2026)

Distributed and Rate-Adaptive Feature Compression
par: Deshmukh, Aditya, et autres
Publié: (2024)

Compressing Chemistry Reveals Functional Groups
par: Sharma, Ruben, et autres
Publié: (2025)

Information-Theoretic Policy Pre-Training with Empowerment
par: Schneider, Moritz, et autres
Publié: (2025)

Score-Based Variational Inference for Inverse Problems
par: Xue, Zhipeng, et autres
Publié: (2024)

Compression Represents Intelligence Linearly
par: Huang, Yuzhen, et autres
Publié: (2024)

AlphaZip: Neural Network-Enhanced Lossless Text Compression
par: Narashiman, Swathi Shree, et autres
Publié: (2024)

Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization
par: Borzechowski, Florian, et autres
Publié: (2025)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
par: Ayonrinde, Kola, et autres
Publié: (2024)

A General Error-Theoretical Analysis Framework for Constructing Compression Strategies
par: Zhang, Boyang, et autres
Publié: (2025)

Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels
par: Hayashi, Yusuke
Publié: (2026)

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
par: Lee, Namyoon, et autres
Publié: (2026)

Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
par: Rinberg, Roy, et autres
Publié: (2026)

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
par: Heurtel-Depeiges, David, et autres
Publié: (2024)

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
par: Pan, Zhixuan, et autres
Publié: (2025)

Laplace Sample Information: Data Informativeness Through a Bayesian Lens
par: Kaiser, Johannes, et autres
Publié: (2025)

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression
par: Kim, Munsik
Publié: (2026)

Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS
par: Obeed, Mohanad, et autres
Publié: (2026)

Redundancy as a Structural Information Principle for Learning and Generalization
par: Bi, Yuda, et autres
Publié: (2025)

Language Modeling Is Compression
par: Delétang, Grégoire, et autres
Publié: (2023)

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
par: Yang, Jiaming, et autres
Publié: (2026)

Generalization and Informativeness of Conformal Prediction
par: Zecchin, Matteo, et autres
Publié: (2024)

Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning
par: Xu, Zhaoqi, et autres
Publié: (2025)

Interpretable Diffusion via Information Decomposition
par: Kong, Xianghao, et autres
Publié: (2023)

Memorization-Compression Cycles Improve Generalization
par: Yu, Fangyuan
Publié: (2025)

An Effective Information Theoretic Framework for Channel Pruning
par: Chen, Yihao, et autres
Publié: (2024)

An Information Criterion for Controlled Disentanglement of Multimodal Data
par: Wang, Chenyu, et autres
Publié: (2024)

An Information-Theoretic Criterion for Efficient Data Synthesis
par: Li, Hanyu, et autres
Publié: (2026)