Copertina

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Yuelin, Yu, Zhenbo, Cheng, Zhengxue, Liu, Wei, Song, Li
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence I.2.6; F.2.2
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
di: Hu, Yuelin, et al.
Pubblicazione: (2026)

AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair
di: Hu, Yuelin, et al.
Pubblicazione: (2026)

Predictable Gradient Manifolds in Deep Learning: Temporal Path-Length and Intrinsic Rank as a Complexity Regime
di: Calvo, Anherutowa
Pubblicazione: (2026)

Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report
di: Wigmore, Jerrod, et al.
Pubblicazione: (2024)

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling
di: Kashyap, Ankit
Pubblicazione: (2025)

StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret Modeling
di: Xu, Zhe
Pubblicazione: (2026)

4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles
di: Zeytuncu, Yunus E.
Pubblicazione: (2026)

Unified Unbiased Variance Estimation for Maximum Mean Discrepancy: Robust Finite-Sample Performance with Imbalanced Data and Exact Acceleration under Null and Alternative Hypotheses
di: Zhong, Shijie, et al.
Pubblicazione: (2026)

Learning Nonlinear Regime Transitions via Semi-Parametric State-Space Models
di: Hiremath, Prakul Sunil
Pubblicazione: (2026)

Causality-Driven Neural Network Repair: Challenges and Opportunities
di: Vares, Fatemeh, et al.
Pubblicazione: (2025)

Grammatically-Guided Sparse Attention for Efficient and Interpretable Transformers
di: Pratyush, Spandan
Pubblicazione: (2026)

Time-to-Injury Forecasting in Elite Female Football: A DeepHit Survival Approach
di: Catterall, Victoria, et al.
Pubblicazione: (2026)

Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous Agents
di: Tiwari, Dhruv
Pubblicazione: (2025)

A Prescriptive Framework for Determining Optimal Days for Short-Term Traffic Counts
di: Mukwaya, Arthur, et al.
Pubblicazione: (2025)

On the approximation capability of GNNs in node classification/regression tasks
di: D'Inverno, Giuseppe Alessio, et al.
Pubblicazione: (2021)

CBR -- Boosting Adaptive Classification By Retrieval of Encrypted Network Traffic with Out-of-distribution
di: Lukach, Amir, et al.
Pubblicazione: (2024)

TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
di: Beck, Florentin, et al.
Pubblicazione: (2025)

The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
di: Arbuzov, Mikhail L., et al.
Pubblicazione: (2026)

Scattered Forest Search: Smarter Code Space Exploration with LLMs
di: Light, Jonathan, et al.
Pubblicazione: (2024)

A Multidisciplinary Approach to Telegram Data Analysis
di: Varbanov, Velizar, et al.
Pubblicazione: (2024)

Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation
di: Santos-Grueiro, Igor
Pubblicazione: (2026)

Reinforcement Learning Controlled Adaptive PSO for Task Offloading in IIoT Edge Computing
di: Perera, Minod, et al.
Pubblicazione: (2025)

Learning Real-Life Approval Elections
di: Faliszewski, Piotr, et al.
Pubblicazione: (2026)

UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
di: Chanda, Prateek, et al.
Pubblicazione: (2026)

Sparse Knowledge Distillation: A Mathematical Framework for Probability-Domain Temperature Scaling and Multi-Stage Compression
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Recursive Meta-Distillation: An Axiomatic Framework for Iterative Knowledge Refinement
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints
di: Buckley, Max, et al.
Pubblicazione: (2025)

When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth
di: Guo, Dongxin, et al.
Pubblicazione: (2026)

CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Models
di: Bömer, Thomas, et al.
Pubblicazione: (2026)

Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration
di: Rodemann, Julian, et al.
Pubblicazione: (2024)

Optimizing Job Allocation using Reinforcement Learning with Graph Neural Networks
di: Quaedvlieg, Lars C. P. M.
Pubblicazione: (2025)

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation
di: Chen, Mu-Chi, et al.
Pubblicazione: (2026)

DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming
di: Malarkkan, Arun Vignesh, et al.
Pubblicazione: (2025)

Enhanced and Efficient Reasoning in Large Learning Models
di: Valiant, Leslie G.
Pubblicazione: (2026)

Vision-Guided Iterative Refinement for Frontend Code Generation
di: Sansford, Hannah, et al.
Pubblicazione: (2026)

Graph Coloring for Multi-Task Learning
di: Patapati, Santosh
Pubblicazione: (2025)

The Hidden Attention of Mamba Models
di: Ali, Ameen, et al.
Pubblicazione: (2024)

LLM Agents for Generating Microservice-based Applications: how complex is your specification?
di: Yellin, Daniel M.
Pubblicazione: (2025)

Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris
di: Wang, Haochuan Kevin
Pubblicazione: (2026)

Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis
di: Sharma, Vansh, et al.
Pubblicazione: (2025)