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

博客园 - 三生石上(FineUI控件)
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
月光博客
月光博客
博客园 - 【当耐特】
Hugging Face - Blog
Hugging Face - Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
博客园_首页
雷峰网
雷峰网
量子位
有赞技术团队
有赞技术团队
博客园 - 叶小钗
博客园 - 聂微东
V
V2EX
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 司徒正美
小众软件
小众软件
The Cloudflare Blog
阮一峰的网络日志
阮一峰的网络日志
Apple Machine Learning Research
Apple Machine Learning Research
Jina AI
Jina AI
人人都是产品经理
人人都是产品经理

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
General Mathematical Proof of Occam's Razor; Upgrading Th...
Gabriel Leuenberger · 2025-06-29 · via cs.IT updates on arXiv.org

This paper's first aim is to prove a modernized Occam's razor beyond a reasonable doubt. To summarize the main argument in one sentence: If we consider all possible, intelligible, scientific models of ever-higher complexity, democratically, the predictions most favored by these complex models will agree with the predictions of the simplest models. This fact can be proven mathematically, thereby validating Occam's razor. Major parts of this line of reasoning have long preexisted within the depths of the algorithmic information theory literature, but they have always left room for doubts of various kinds. Therefore, we increase the generality, completeness, clarity, accessibility, and credibility of these arguments by countering over a dozen objections. We build our mathematical proof of Occam's razor on the shoulders of the exact 'chain rule' for Kolmogorov complexity. Concerning physics, we then go on to diagnose the primary amendable root cause of the present stagnation of the research field of fundamental theoretical physics. We show that the effective antidote would consist in a practically feasible upgrade to the theoretical physicists' research methodology: When proposing new theoretical models, physicists should simply calculate and report the total amount of information that their models consist of. We explain why this methodology would be highly effective as well as how these calculations could be performed efficiently.