Cover Image

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Weiqi, Tian, Zhiyi, Zhang, Chenhan, Yu, Shui
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning
by: Wang, Weiqi, et al.
Published: (2026)

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

Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
by: Federici, Marco, et al.
Published: (2023)

The Causal Information Bottleneck and Optimal Causal Variable Abstractions
by: Simoes, Francisco N. F. Q., et al.
Published: (2024)

SMS: Self-supervised Model Seeding for Verification of Machine Unlearning
by: Wang, Weiqi, et al.
Published: (2025)

The Alignment Bottleneck
by: Cao, Wenjun
Published: (2025)

Machine Unlearning: A Comprehensive Survey
by: Wang, Weiqi, et al.
Published: (2024)

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
by: Oomerjee, Adnan, et al.
Published: (2025)

A General Error-Theoretical Analysis Framework for Constructing Compression Strategies
by: Zhang, Boyang, et al.
Published: (2025)

SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
by: Wang, Weiqi, et al.
Published: (2025)

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
by: Pan, Zhixuan, et al.
Published: (2025)

BlindU: Blind Machine Unlearning without Revealing Erasing Data
by: Wang, Weiqi, et al.
Published: (2026)

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
by: Heurtel-Depeiges, David, et al.
Published: (2024)

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

Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition
by: Tian, Chao, et al.
Published: (2025)

The Information of Large Language Model Geometry
by: Tan, Zhiquan, et al.
Published: (2024)

Compressing Chemistry Reveals Functional Groups
by: Sharma, Ruben, et al.
Published: (2025)

Distributed and Rate-Adaptive Feature Compression
by: Deshmukh, Aditya, et al.
Published: (2024)

Statistically Valid Information Bottleneck via Multiple Hypothesis Testing
by: Farzaneh, Amirmohammad, et al.
Published: (2024)

Interpretable Diffusion via Information Decomposition
by: Kong, Xianghao, et al.
Published: (2023)

Memorization-Compression Cycles Improve Generalization
by: Yu, Fangyuan
Published: (2025)

Machine Unlearning via Information Theoretic Regularization
by: Xu, Shizhou, et al.
Published: (2025)

Two-Dimensional Quantization for Geometry-Aware Audio Coding
by: Shuster, Tal, et al.
Published: (2025)

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

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

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

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
by: Lee, Namyoon, et al.
Published: (2026)

Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
by: Rinberg, Roy, et al.
Published: (2026)

An Information Criterion for Controlled Disentanglement of Multimodal Data
by: Wang, Chenyu, et al.
Published: (2024)

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
by: Yang, Jiaming, et al.
Published: (2026)

A Distance Metric Learning Model Based On Variational Information Bottleneck
by: Zhang, YaoDan, et al.
Published: (2024)

The Normalized Cross Density Functional: A Framework to Quantify Statistical Dependence for Random Processes
by: Hu, Bo, et al.
Published: (2022)

Compression Represents Intelligence Linearly
by: Huang, Yuzhen, et al.
Published: (2024)

Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning
by: Xu, Zhaoqi, et al.
Published: (2025)

An Effective Information Theoretic Framework for Channel Pruning
by: Chen, Yihao, et al.
Published: (2024)

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

Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimation
by: Nichani, Arjun, et al.
Published: (2026)

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
by: Bhattacharjee, Payel, et al.
Published: (2026)

Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection
by: Salami, Dariush, et al.
Published: (2025)

Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
by: Sharma, Jai, et al.
Published: (2026)