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
Threatpost
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
T
The Blog of Author Tim Ferriss
S
SegmentFault 最新的问题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博
博客园 - 司徒正美
T
Tailwind CSS Blog
The Cloudflare Blog
The Last Watchdog
The Last Watchdog
PCI Perspectives
PCI Perspectives
博
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
TaoSecurity Blog
TaoSecurity Blog
云风的 BLOG
云风的 BLOG
C
Cybersecurity and Infrastructure Security Agency CISA
O
OpenAI News
Recorded Future
Recorded Future
GbyAI
GbyAI
www.infosecurity-magazine.com
www.infosecurity-magazine.com
Y
Y Combinator Blog
D
Darknet – Hacking Tools, Hacker News & Cyber Security
量
量子位
博
博客园 - 叶小钗
V
Vulnerabilities – Threatpost
F
Full Disclosure
Recent Announcements
Recent Announcements
Vercel News
Vercel News
S
Schneier on Security
H
Heimdal Security Blog
Cisco Talos Blog
Cisco Talos Blog
V2EX - 技术
V2EX - 技术
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
B
Blog RSS Feed
宝玉的分享
宝玉的分享
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
P
Privacy & Cybersecurity Law Blog
T
Threat Research - Cisco Blogs
G
Google Developers Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
爱范儿
爱范儿
IT之家
IT之家
大猫的无限游戏
大猫的无限游戏
C
Check Point Blog
N
Netflix TechBlog - Medium
S
Security @ Cisco Blogs
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Microsoft Azure Blog
Microsoft Azure Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Cyberwarzone
Cyberwarzone

math updates on arXiv.org

Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization Non-normal spectral signatures of instability in neural network training dynamics Optimization of randomized neural networks for transfer operator approximation Selective Ambulance Dispatch Under Contextual Travel-Time Uncertainty LLAMA LIMA: A Living Meta-Analysis on the Effects of Generative AI on Learning Mathematics Learning Decision-Sufficient Representations for Linear Optimization Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses Prabhakar function and unified fractional kinetic equation in bicomplex space Computing Gamma(p/q) with Beta function values Flows on Graded Manifolds Optimal embedding dimension in the Nash--Tognoli theorem 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 Invariants of real affine varieties based on their complexifications Topological symmetric and braid homologies A Formal Graph-Theoretic Framework for Pitch Class Set Analysis Finite groups with high commuting probability for Sylow subgroups 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 Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy Training-Free Looped Transformers Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries Asymmetric Scaling Laws from Sparse Features Is Dimensionality a Barrier for Retrieval Models? RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs Commutator-Induced Uncertainty in VAEs Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating Generalized Stochastic Approximation of the Log-Likelihood Ratio for Robust Sequential Change-Point Detection Instance-Optimal Estimation with Multiple LLM Judges on a Budget Entropy Equivalence Testing Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation Any-Dimensional Invariant Universality Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models Anytime Training with Schedule-Free Spectral Optimization Concise and elegant proofs of three formulas for complete Bell polynomials On Reed-Muller subcodes, Grassmannian partitions and sum-free functions Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology The General Theory of Localization Methods A Comprehensive Study of Clique Graphs and Clique Regular Graphs Every signed planar graph is $5$-choosable: A short proof and refinements General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels Proximal basin hopping: global optimization with guarantees Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers Stochastic Non-Smooth Convex Optimization with Unbounded Gradients Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space The Geometry of Cooperative Game Solutions: Stratified Egalitarian Shapley Values An Axiomatic Theory of Tie-Breaking: Impossibility, Characterization, and Decomposition PyCSP3-Scheduling: A Scheduling Extension for PyCSP3 Strategic PAC Learnability via Geometric Definability Proximal-Based Generative Modeling for Bayesian Inverse Problems Every Minimal Counterexample to the Erdős-Gyárfás Conjecture is Predominantly Cubic SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference NOVA: Fundamental Limits of Knowledge Discovery Through AI Model-based Bootstrap of Controlled Markov Chains TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects Omni-scale Learning-based Sequential Decision Framework for Order Fulfillment of Tote-handling Robotic Systems Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes Towards an Inferentialist Account of Information Through Proof-theoretic Semantics Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization Robust and Fast Training via Per-Sample Clipping Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems Information-Theoretic Measures in AI: A Practical Decision Guide Inference of Online Newton Methods with Nesterov's Accelerated Sketching A Unified Fractional Regularization Framework for Sparse Recovery Mathematical Foundations for Peer-to-Peer Lattice Computation Geometric Layer-wise Approximation Rates for Deep Networks RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory ML-based approach to classification and generation of structured light propagation in turbulent media Zeroth-Order Optimization at the Edge of Stability Adaptive Learning via Off-Model Training and Importance Sampling for Fully Non-Markovian Optimal Stochastic Control. Complete version Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes Training-Free Rate-Distortion-Perception Traversal With Diffusion Conformal Policy Control Linear Regression with Unknown Truncation Beyond Gaussian Features ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport Feature Learning Dynamics in Infinite-Depth Neural Networks ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms Normalizing Flows on Quotient Manifolds via Boundary Quotients What Can Be Recovered Under Sparse Adversarial Corruption? Assumption-Free Theory for Linear Measurements TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis Program Evaluation with Remotely Sensed Outcomes Efficient Gradient Estimation for Parameterized Quantum Systems with Lie Algebraic Symmetries
Restart and Adaptive Acceleration in Stochastic Gradient Methods
[Submitted on 19 Jun 2026] · 2026-06-23 · via math updates on arXiv.org

View PDF

Abstract:We study restart schemes in stochastic optimization problems for non-smooth and weakly convex that satisfy a Kurdyka-Łojasiewicz inequality. We show that using restarts allows us to leverage the KŁ inequalities to achieve improved rates of convergence, with acceleration depending explicitly on the KŁ exponent. Furthermore, optimal restart schedules lead to learning-rates akin to Polyak steps for SGD. While regularity constants such as the KŁ exponent are typically unknown in practice, we prove that restart schemes are robust to a significant misspecification of these constants, hence nearly adaptive. We detail numerical experiments on both toy problems, where the KŁ exponent is controlled, and training of Large Language Models (LLMs).

Submission history

From: Alexandre D'Aspremont [view email]
[v1] Fri, 19 Jun 2026 11:54:49 UTC (283 KB)

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。