惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
Tailwind CSS Blog
博客园 - Franky
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Y
Y Combinator Blog
Hugging Face - Blog
Hugging Face - Blog
博客园 - 聂微东
L
LangChain Blog
博客园_首页
Recent Announcements
Recent Announcements
月光博客
月光博客
酷 壳 – CoolShell
酷 壳 – CoolShell
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
H
Hackread – Cybersecurity News, Data Breaches, AI and More
爱范儿
爱范儿
博客园 - 叶小钗
博客园 - 【当耐特】
The Cloudflare Blog
J
Java Code Geeks
G
Google Developers Blog
云风的 BLOG
云风的 BLOG
Blog — PlanetScale
Blog — PlanetScale
博客园 - 司徒正美
aimingoo的专栏
aimingoo的专栏
A
About on SuperTechFans

cs.IT updates on arXiv.org

Theoretical Limits of Language Model Alignment $f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval Expert Routing for Communication-Efficient MoE via Finite Expert Banks Contextual Memory-Enhanced Source Coding for Low-SNR Communications Realizable Bayes-Consistency for General Metric Losses Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy Optimization of CV-QKD Under Practical Constraints Benchmarking Wireless Representations: High-Dimensional vs. Compressed Embeddings for Efficiency and Robustness Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimation Evolving Token Communication with Parametric Memory Network Remote Action Generation: Remote Control with Minimal Communication The (Marginal) Value of a Search Ad: An Online Causal Framework for Repeated Second-price Auctions Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation Linear-Readout Floors and Threshold Recovery in Computation in Superposition Soft Graph Diffusion Transformer for MIMO Detection Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design Exponential families from a single KL identity MIFair: A Mutual-Information Framework for Intersectionality and Multiclass Fairness Diffusion-OAMP for Joint Image Compression and Wireless Transmission Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
Strong Converse Bounds for Compression of Mixed States
Zahra Baghali Khanian · 2022-06-19 · via cs.IT updates on arXiv.org

In this paper, we study strong converse properties for both visible and blind compression of mixed states. The optimal rate of a visible compression scheme is obtained in terms of the entanglement of purification, whose additivity remains unknown so far. For a variation of extendible states, we prove that the entanglement of purification is additive and apply this to obtain a "pretty strong" converse bound for the blind and visible compression of such states. Namely, when the rate decreases below the optimal rate, the error exhibits a discontinuous jump from 0 to at least $\frac{1}{3\sqrt{2}}$. To deal with the visible case for general states, we define a new quantity $E_{α,p}(A:R)_ρ$ for a bipartite state $ρ^{AR}$ and $α\in (0,1)\cup (1,\infty)$ as the $α$-Rényi generalization of the entanglement of purification $E_{p}(A:R)_ρ$. For $α=1$, we define $E_{1,p}(A:R)_ρ:=E_{p}(A:R)_ρ$. We show that for any rate below the regularization $\lim_{α\to 1^+}E_{α,p}^{\infty}(A:R)_ρ:=\lim_{α\to 1^+} \lim_{n \to \infty} \frac{E_{α,p}(A^n:R^n)_{ρ^{\otimes n}}}{n}$ the fidelity for the visible compression exponentially converges to zero. Moreover, we consider blind compression of a general mixed-state source $ρ^{AR}$ shared between an encoder and an inaccessible reference system $R$. We obtain a strong converse bound for the compression of this source by assuming that the decoder is a super-unital channel. This immediately implies a strong converse for the blind compression of ensembles of mixed states, by assuming a super-unital decoder, as this is a special case of the general mixed-state source $ρ^{AR}$ where the reference system $R$ has a classical structure.