Copertina

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chang, Hoyeon, Mucsányi, Bálint, Oh, Seong Joon
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Characterizing Pattern Matching and Its Limits on Compositional Task Structures
di: Chang, Hoyeon, et al.
Pubblicazione: (2025)

Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints
di: Rácz, Dániel, et al.
Pubblicazione: (2024)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
di: Hedar, Abdel-Rahman, et al.
Pubblicazione: (2024)

Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State
di: Zhu, Peiying, et al.
Pubblicazione: (2026)

SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel
di: Luna, Jose Miguel, et al.
Pubblicazione: (2026)

A Simple Generalisation of the Implicit Dynamics of In-Context Learning
di: Innocenti, Francesco, et al.
Pubblicazione: (2025)

Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
di: Ma, Zhenyao, et al.
Pubblicazione: (2026)

Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks
di: Wang, Yumeng, et al.
Pubblicazione: (2025)

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
di: Xu, Yongzhong
Pubblicazione: (2026)

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
di: Liu, Weijie, et al.
Pubblicazione: (2023)

DataRater: Meta-Learned Dataset Curation
di: Calian, Dan A., et al.
Pubblicazione: (2025)

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
di: Zhao, Xingyu, et al.
Pubblicazione: (2026)

Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
di: Riscos, Pablo de los, et al.
Pubblicazione: (2024)

Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
di: Lin, Zezheng, et al.
Pubblicazione: (2026)

Fusion-Based Neural Generalization for Predicting Temperature Fields in Industrial PET Preform Heating
di: Alsheikh, Ahmad, et al.
Pubblicazione: (2025)

ParalESN: Enabling parallel information processing in Reservoir Computing
di: Pinna, Matteo, et al.
Pubblicazione: (2026)

Understanding Goal Generalisation in Sequential Reinforcement Learning
di: Brown, Jason Ross, et al.
Pubblicazione: (2026)

What changes after deployment? A survey on On-device Learning in TinyML
di: Pavan, Massimo, et al.
Pubblicazione: (2026)

Bounded Ratio Reinforcement Learning
di: Ao, Yunke, et al.
Pubblicazione: (2026)

Extending Differential Temporal Difference Methods for Episodic Problems
di: De Asis, Kris, et al.
Pubblicazione: (2026)

Democratic Preference Alignment via Sortition-Weighted RLHF
di: Sana, Suvadip, et al.
Pubblicazione: (2026)

Architectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt Detection
di: Noon, Jay
Pubblicazione: (2026)

Interestingness as an Inductive Heuristic for Future Compression Progress
di: Herrmann, Vincent, et al.
Pubblicazione: (2026)

Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
di: Kohlberger, Björn Roman
Pubblicazione: (2026)

Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
di: Yıldırım, Alper
Pubblicazione: (2026)

Path-Coupled Bellman Flows for Distributional Reinforcement Learning
di: Xu, Boyang, et al.
Pubblicazione: (2026)

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
di: Liu, Weijie, et al.
Pubblicazione: (2025)

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator
di: Furuyama, Ryoma, et al.
Pubblicazione: (2024)

Manipulating Predictions over Discrete Inputs in Machine Teaching
di: Wu, Xiaodong, et al.
Pubblicazione: (2024)

Axiomatic Characterisations of Sample-based Explainers
di: Amgoud, Leila, et al.
Pubblicazione: (2024)

The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm
di: Birnick, Johann
Pubblicazione: (2025)

Evaluation of post-hoc interpretability methods in time-series classification
di: Turbé, Hugues, et al.
Pubblicazione: (2022)

Resilience to the Flowing Unknown: an Open Set Recognition Framework for Data Streams
di: Barcina-Blanco, Marcos, et al.
Pubblicazione: (2024)

Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
di: Wang, Yuhui, et al.
Pubblicazione: (2024)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
di: Ha, SeungBum, et al.
Pubblicazione: (2025)

Residual Reservoir Memory Networks
di: Pinna, Matteo, et al.
Pubblicazione: (2025)

Individual Fairness Through Reweighting and Tuning
di: Mahamadou, Abdoul Jalil Djiberou, et al.
Pubblicazione: (2024)

Evaluating the effectiveness of predicting covariates in LSTM Networks for Time Series Forecasting
di: Davies, Gareth
Pubblicazione: (2024)

FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
di: Tian, Tian, et al.
Pubblicazione: (2025)

Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
di: Pinna, Matteo, et al.
Pubblicazione: (2025)