Copertina

Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Medeiros, Daniel Nobrega
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence 68T07, 49M37 I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PolyGLU: State-Conditional Activation Routing in Transformer Feed-Forward Networks
di: Medeiros, Daniel Nobrega
Pubblicazione: (2026)

On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
di: Li, Zhong, et al.
Pubblicazione: (2020)

Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection
di: Lau, Matthew, et al.
Pubblicazione: (2023)

TACIT: Transformation-Aware Capturing of Implicit Thought
di: Nobrega, Daniel
Pubblicazione: (2026)

NeuronSpark: A Spiking Neural Network Language Model with Selective State Space Dynamics
di: Tang, Zhengzheng
Pubblicazione: (2026)

Multi-Level Fusion Graph Neural Network for Molecule Property Prediction
di: Liu, XiaYu, et al.
Pubblicazione: (2025)

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
di: Zhou, Xueyang, et al.
Pubblicazione: (2025)

Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
di: Parris, William
Pubblicazione: (2026)

Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks
di: Qu, Xiran, et al.
Pubblicazione: (2023)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
di: Yamchote, Phaphontee, et al.
Pubblicazione: (2025)

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
di: Pepe, Alberto, et al.
Pubblicazione: (2026)

Stabilized Adaptive Loss and Residual-Based Collocation for Physics-Informed Neural Networks
di: Singh, Divyavardhan, et al.
Pubblicazione: (2026)

BreakFun: Jailbreaking LLMs via Schema Exploitation
di: Oskooei, Amirkia Rafiei, et al.
Pubblicazione: (2025)

Velocity-Inferred Hamiltonian Neural Networks: Learning Energy-Conserving Dynamics from Position-Only Data
di: Xu, Ruichen, et al.
Pubblicazione: (2025)

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
di: Das, Sourav
Pubblicazione: (2026)

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
di: Jeong, Kyungwon, et al.
Pubblicazione: (2026)

Simple Network Graph Comparative Learning
di: Yu, Qiang, et al.
Pubblicazione: (2026)

cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
di: Giannini, Federico, et al.
Pubblicazione: (2026)

Task-Synchronized Recurrent Neural Networks
di: Lukoševičius, Mantas, et al.
Pubblicazione: (2022)

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
di: Turan, Berkant, et al.
Pubblicazione: (2025)

Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
di: Alnemari, Mohammed, et al.
Pubblicazione: (2026)

Predicting Music Track Popularity by Convolutional Neural Networks on Spotify Features and Spectrogram of Audio Waveform
di: Falah, Navid, et al.
Pubblicazione: (2025)

Metriplector: From Field Theory to Neural Architecture
di: Oprisa, Dan, et al.
Pubblicazione: (2026)

HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learning
di: Dang, Long H, et al.
Pubblicazione: (2025)

QGraphLIME - Explaining Quantum Graph Neural Networks
di: Jena, Haribandhu, et al.
Pubblicazione: (2025)

Evaluation of Differential Privacy Mechanisms on Federated Learning
di: Varsani, Tejash
Pubblicazione: (2025)

Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero
di: Maggiolo, Matteo, et al.
Pubblicazione: (2025)

Model compression using knowledge distillation with integrated gradients
di: Hernandez, David E., et al.
Pubblicazione: (2025)

Inverse Boundary Value and Optimal Control Problems on Graphs: A Neural and Numerical Synthesis
di: Garrousian, Mehdi, et al.
Pubblicazione: (2022)

Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradients
di: Hernandez, David E., et al.
Pubblicazione: (2025)

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
di: Wu, Chengcan, et al.
Pubblicazione: (2025)

A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
di: Leyli-Abadi, Milad, et al.
Pubblicazione: (2026)

HGTUL: A Hypergraph-based Model For Trajectory User Linking
di: Chang, Fengjie, et al.
Pubblicazione: (2025)

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
di: Książek, Kamil, et al.
Pubblicazione: (2023)

Is ReLU Adversarially Robust?
di: Sooksatra, Korn, et al.
Pubblicazione: (2024)

Upside Down Reinforcement Learning with Policy Generators
di: Di Ventura, Jacopo, et al.
Pubblicazione: (2025)

CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution Generalization
di: Chowdhury, Jawad, et al.
Pubblicazione: (2024)

Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching
di: Ricciardi, Antonio Pio, et al.
Pubblicazione: (2025)

Adversarial Patch Attacks on Vision-Based Cargo Occupancy Estimation via Differentiable 3D Simulation
di: Hedna, Mohamed Rissal, et al.
Pubblicazione: (2025)

Harnessing non-adversarial robustness in large language models
di: Zhou, Qinghua, et al.
Pubblicazione: (2026)