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

U
Unit 42
V
V2EX
Martin Fowler
Martin Fowler
博
博客园 - Franky
P
Proofpoint News Feed
P
Palo Alto Networks Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
B
Blog
The Register - Security
The Register - Security
Latest news
Latest news
S
Security @ Cisco Blogs
Simon Willison's Weblog
Simon Willison's Weblog
Recorded Future
Recorded Future
大猫的无限游戏
大猫的无限游戏
M
Microsoft Research Blog - Microsoft Research
Scott Helme
Scott Helme
T
Tailwind CSS Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Application and Cybersecurity Blog
Application and Cybersecurity Blog
T
True Tiger Recordings
有赞技术团队
有赞技术团队
I
Intezer
Cisco Talos Blog
Cisco Talos Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
The GitHub Blog
The GitHub Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
T
Tenable Blog
博
博客园 - 叶小钗
Hugging Face - Blog
Hugging Face - Blog
Hacker News: Ask HN
Hacker News: Ask HN
S
Security Archives - TechRepublic
F
Future of Privacy Forum
爱范儿
爱范儿
PCI Perspectives
PCI Perspectives
H
Help Net Security
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
T
The Blog of Author Tim Ferriss
MyScale Blog
MyScale Blog
N
Netflix TechBlog - Medium
罗
罗磊的独立博客
Apple Machine Learning Research
Apple Machine Learning Research
MongoDB | Blog
MongoDB | Blog
Security Latest
Security Latest
美
美团技术团队
博
博客园 - 三生石上(FineUI控件)
S
Schneier on Security
量
量子位
C
CERT Recently Published Vulnerability Notes
SecWiki News
SecWiki News

cs.LG updates on arXiv.org

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting Manifold-Guided Attention Steering $\textit{BlockFormer}$ : Transformer-based inference from interaction maps TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems Three Costs of Amortizing Gaussian Process Inference with Neural Processes Toward Understanding Adversarial Distillation: Why Robust Teachers Fail Aerodynamic force reconstruction using physics-informed Gaussian processes Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning Symbolic Density Estimation for Discrete Distributions Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes IKNO: Infinite-order Kernel Neural Operators Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models Provable Joint Decontamination for Benchmarking Multiple Large Language Models An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning Double descent for least-squares interpolation on contaminated data: A simulation study Harnesses for Inference-Time Alignment over Execution Trajectories Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation CausalGuard: Conformal Inference under Graph Uncertainty LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation Dynamic Mixture of Latent Memories for Self-Evolving Agents Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines One-Way Policy Optimization for Self-Evolving LLMs How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction AgForce Enables Antigen-conditioned Generative Antibody Design Predicting Performance of Symbolic and Prompt Programs with Examples I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs Tabular foundation models for robust calibration of near-infrared chemical sensing data Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos Noise Schedule Design for Diffusion Models: An Optimal Control Perspective Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have) X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation EntmaxKV: Support-Aware Decoding for Entmax Attention From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction Value-Gradient Hypothesis of RL for LLMs From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Hierarchical Variational Policies for Reward-Guided Diffusion Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure? Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines Distributed Direct Preference Optimization Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
Heeyun Heo, · 2026-05-23 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:In competitive games, players frequently switch strategies after losing streaks, yet our analysis of 926,334 match records from 34,619 Clash Royale players reveals a counterintuitive pattern: switching frequency is inversely associated with the win rate, with effects that vary substantially across players and situational contexts. We attribute this to a limitation common in many prior recommendation systems, which evaluate strategies by expected quality while overlooking the behavioral cost of switching and individual differences in switching propensity. We refer to this implicit premise as the Zero Switching Cost Assumption. To address this, we reformulate strategy recommendation as a transition-level decision problem and instantiate it as TQP (Transition Quality Predictor), a three-stage pipeline structured as Who -> When -> What. PersonaGate suppresses recommendations for players whose strategic consistency is empirically associated with superior outcomes. TimingGate identifies moments when switching is likely to yield a net benefit over staying, using a subtype- and state-matched baseline to control for natural win-rate recovery. ScoreFusion ranks candidate strategies by combining an adoptability signal with predicted transition quality (delta WR). We further introduce SwitchGap, an evaluation metric that measures a policy's discriminative quality without treating observed player choices as optimal ground truth. This property is particularly important because the most frequent switchers record the lowest win rates. The full pipeline achieves a SwitchGap of +10.4 percentage points at a recommendation rate of 5.4%, and loss-triggered switchers, despite being the lowest-performing group, benefit the most from subtype-conditioned guidance.
Comments: 11 pages, 2 figures, 4 tables; Accepted at IEEE Conference on Games (CoG) 2026
Subjects: Machine Learning (cs.LG)
Cite as: arXiv:2605.21868 [cs.LG]
  (or arXiv:2605.21868v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.21868

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Heeyun Heo [view email]
[v1] Thu, 21 May 2026 01:28:19 UTC (1,907 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。