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

Recent Announcements
Recent Announcements
Martin Fowler
Martin Fowler
MongoDB | Blog
MongoDB | Blog
Engineering at Meta
Engineering at Meta
Stack Overflow Blog
Stack Overflow Blog
Google DeepMind News
Google DeepMind News
Microsoft Security Blog
Microsoft Security Blog
aimingoo的专栏
aimingoo的专栏
I
InfoQ
B
Blog
WordPress大学
WordPress大学
Jina AI
Jina AI
小众软件
小众软件
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园_首页
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
酷 壳 – CoolShell
酷 壳 – CoolShell
阮一峰的网络日志
阮一峰的网络日志
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
G
Google Developers Blog
C
Check Point Blog
月光博客
月光博客
L
LangChain Blog
GbyAI
GbyAI

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
The Origin of the Inaccessible Game
Neil D. Lawrence · 2026-01-19 · via cs.IT updates on arXiv.org

The inaccessible game is an information-geometric framework where dynamics of information loss emerge from maximum entropy production under marginal-entropy conservation. We study the game's starting state, the origin. Classical Shannon entropy forbids a representation with zero joint entropy and positive marginal entropies: non-negativity of conditional entropy rules this out. Replacing Shannon with von Neumann entropy within the Baez Fritz Leinster Parzygnat categorical framework removes this obstruction and admits a well-defined origin: a globally pure state with maximally mixed marginals, selected up to local-unitary equivalence. At this LME origin, marginal-entropy conservation becomes a second-order geometric condition. Because the marginal-entropy sum is saturated termwise, the constraint gradient vanishes and first-order tangency is vacuous; admissible directions are selected by the kernel of the constraint Hessian, characterised by the marginal-preserving tangent space. We derive the constrained gradient flow in the matrix exponential family and show that, as the origin is approached, the affine time parameter degenerates. This motivates an axiomatically distinguished reparametrisation, entropy time $t$, defined by $dH/dt = c$ for fixed constant $c>0$. In this parametrisation, the infinite affine-time approach to the boundary maps to a finite entropy-time interval. The constrained dynamics split into a symmetric dissipative component realising SEA and a reversible component represented as unitary evolution. As in the classical game, marginal-entropy conservation is equivalent to conservation of a sum of local modular Hamiltonian expectations, a state-dependent "modular energy"; in Gibbs regimes where local modular generators become approximately parameter-invariant, this reduces to familiar fixed-energy constraints from nonequilibrium thermodynamics.