Geometry of Lightning Self-Attention: Identifiability and Dimension - 惯性聚合

推荐订阅源

OSCHINA 社区最新新闻

Recorded Future

Blog — PlanetScale

Stack Overflow Blog

Google DeepMind News

Full Disclosure

博客园 - Franky

Privacy International News Feed

The Hacker News

Last Week in AI

LINUX DO - 热门话题

Vulnerabilities – Threatpost

Threat Intelligence Blog | Flashpoint

美团技术团队

Y Combinator Blog

Security Latest

CERT Recently Published Vulnerability Notes

Proofpoint News Feed

CTFtime.org: upcoming CTF events

SegmentFault 最新的问题

Cisco Talos Blog

Lohrmann on Cybersecurity

Cybersecurity and Infrastructure Security Agency CISA

Privacy & Cybersecurity Law Blog

Cyber Attacks, Cyber Crime and Cyber Security

CXSECURITY Database RSS Feed - CXSecurity.com

The Register - Security

Tailwind CSS Blog

Palo Alto Networks Blog

Microsoft Security Blog

Darknet – Hacking Tools, Hacker News & Cyber Security

math updates on arXiv.org

PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels Anytime Training with Schedule-Free Spectral Optimization Any-Dimensional Invariant Universality Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation Instance-Optimal Estimation with Multiple LLM Judges on a Budget Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization Commutator-Induced Uncertainty in VAEs Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them Non-normal spectral signatures of instability in neural network training dynamics Is Dimensionality a Barrier for Retrieval Models? Optimization of randomized neural networks for transfer operator approximation Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries Training-Free Looped Transformers LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models Entropy Equivalence Testing Selective Ambulance Dispatch Under Contextual Travel-Time Uncertainty Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating Asymmetric Scaling Laws from Sparse Features Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport Efficient Gradient Estimation for Parameterized Quantum Systems with Lie Algebraic Symmetries LLAMA LIMA: A Living Meta-Analysis on the Effects of Generative AI on Learning Mathematics Linear Regression with Unknown Truncation Beyond Gaussian Features Training-Free Rate-Distortion-Perception Traversal With Diffusion Learning Decision-Sufficient Representations for Linear Optimization Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses Every Minimal Counterexample to the Erdős-Gyárfás Conjecture is Predominantly Cubic Prabhakar function and unified fractional kinetic equation in bicomplex space Every signed planar graph is $5$-choosable: A short proof and refinements A Comprehensive Study of Clique Graphs and Clique Regular Graphs Mathematical Foundations for Peer-to-Peer Lattice Computation Computing Gamma(p/q) with Beta function values Flows on Graded Manifolds Optimal embedding dimension in the Nash--Tognoli theorem Generalized Stochastic Approximation of the Log-Likelihood Ratio for Robust Sequential Change-Point Detection An optimal first-order method for smooth and strongly convex composite optimization and its stationary limit Sharp Bohr-Type inequalities for certain classes of close-to-convex functions An Axiomatic Theory of Tie-Breaking: Impossibility, Characterization, and Decomposition Invariants of real affine varieties based on their complexifications The Geometry of Cooperative Game Solutions: Stratified Egalitarian Shapley Values Topological symmetric and braid homologies Reconstructibility of Pitch Class Graphs and the Z-relation Finite groups with high commuting probability for Sylow subgroups On Reed-Muller subcodes, Grassmannian partitions and sum-free functions Concise and elegant proofs of three formulas for complete Bell polynomials Performance Bounds for Rollout Policies in Stochastic Shortest Path Problems Real 2-blocks in quasi-simple groups Maximal subalgebras of the Lie algebra $W_n(\mathbb{K})$ Cohomogeneity-One Ruled Hypersurfaces in $\mathbb{CP}^2$ and $\mathbb{C}H^2$ Global analysis of the Kuramoto flow Cartier algebras through the lens of $p$-families Positivity in the context of Hodge modules and Higgs bundles on Deligne-Mumford stacks Symplectic lattice counting and zeta functions of higher Heisenberg groups A Complete Spectral Analysis of the CEV Operator with Applications to Arbitrage A secondary pairing between K-theory and K-homology, relative eta invariants, and zeta maps Detecting and Correcting Sample-by-Sample Scale Distortion in RNA Sequencing Data Star-Shaped Integral Cartan-Type Matrices and an Egyptian-Fraction Classification of Affine Weighted Trees The Poisson Tail Conjecture for Primes in Short Intervals Polylogarithmic Full-Chord Buffon Discrepancy Extremum seeking with exponential convergence via high-order Lie bracket approximations Sets of large values of polynomial multi-correlation functions Reflections and Sheafifications in Algebraic and Topological Categories On the final-state problem for the 1D cubic NLS Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression Isotropic Meta Kazhdan-Lusztig Combinatorics II: Isomorphism to the generalised Khovanov arc algebra Improved Torn Paper Coding via Local Alignment Discrete Pauli pairs Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations The General Theory of Localization Methods TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference Program Evaluation with Remotely Sensed Outcomes Proximal basin hopping: global optimization with guarantees Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches NOVA: Fundamental Limits of Knowledge Discovery Through AI Stochastic Non-Smooth Convex Optimization with Unbounded Gradients PyCSP3-Scheduling: A Scheduling Extension for PyCSP3 Strategic PAC Learnability via Geometric Definability Proximal-Based Generative Modeling for Bayesian Inverse Problems Feature Learning Dynamics in Infinite-Depth Neural Networks TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection Omni-scale Learning-based Sequential Decision Framework for Order Fulfillment of Tote-handling Robotic Systems Towards an Inferentialist Account of Information Through Proof-theoretic Semantics Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes Normalizing Flows on Quotient Manifolds via Boundary Quotients Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots A Unified Fractional Regularization Framework for Sparse Recovery Inference of Online Newton Methods with Nesterov's Accelerated Sketching Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data Adaptive Learning via Off-Model Training and Importance Sampling for Fully Non-Markovian Optimal Stochastic Control. Complete version

Geometry of Lightning Self-Attention: Identifiability and Dimension

[Submitted on 30 Aug 2024 (v1), last revised 11 Jun 2026 (this v · 2026-06-12 · via math updates on arXiv.org

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。