Imagen de Portada

Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Taeyoung, Kang, Myungjoo
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Analysis of Fourier Neural Operators via Effective Field Theory
por: Kim, Taeyoung
Publicado: (2025)

Approximating Numerical Fluxes Using Fourier Neural Operators for Hyperbolic Conservation Laws
por: Kim, Taeyoung, et al.
Publicado: (2024)

Loop Corrections to the Training Error and Generalization Gap of Random Feature Models
por: Kim, Taeyoung
Publicado: (2026)

Neural Operators Learn the Local Physics of Magnetohydrodynamics
por: Kim, Taeyoung, et al.
Publicado: (2024)

MoDEx: Mixture of Depth-specific Experts for Multivariate Long-term Time Series Forecasting
por: Yoon, Hyekyung, et al.
Publicado: (2026)

Why Federated Optimization Fails to Achieve Perfect Fitting? A Theoretical Perspective on Client-Side Optima
por: Lei, Zhongxiang, et al.
Publicado: (2025)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
por: Ke, Yekun, et al.
Publicado: (2024)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
por: Öncel, Fırat, et al.
Publicado: (2024)

Why Do Transformers Fail to Forecast Time Series In-Context?
por: Zhou, Yufa, et al.
Publicado: (2025)

To Predict or Not To Predict? Proportionally Masked Autoencoders for Tabular Data Imputation
por: Kim, Jungkyu, et al.
Publicado: (2024)

MINR: Implicit Neural Representations with Masked Image Modelling
por: Lee, Sua, et al.
Publicado: (2025)

Why and How Auxiliary Tasks Improve JEPA Representations
por: Yu, Jiacan, et al.
Publicado: (2025)

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
por: Qiu, Haiquan, et al.
Publicado: (2025)

Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
por: Denisov-Blanch, Yegor, et al.
Publicado: (2026)

ReDi: Rectified Discrete Flow
por: Yoo, Jaehoon, et al.
Publicado: (2025)

Feature-aligned N-BEATS with Sinkhorn divergence
por: Lee, Joonhun, et al.
Publicado: (2023)

The Scaling Law of Evaluation Failure: Why Simple Averaging Collapses Under Data Sparsity and Item Difficulty Gaps, and How Item Response Theory Recovers Ground Truth Across Domains
por: Kang, Jung Min
Publicado: (2026)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
por: Cao, Yuan-dong, et al.
Publicado: (2026)

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks
por: Moriai, Ryo, et al.
Publicado: (2025)

Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
por: Gupta, Isha, et al.
Publicado: (2025)

Improving the Training of Rectified Flows
por: Lee, Sangyun, et al.
Publicado: (2024)

Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning
por: Yang, Zhe-Rui, et al.
Publicado: (2024)

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
por: Hou, Hongru, et al.
Publicado: (2026)

The Infinite-Dimensional Nature of Spectroscopy and Why Models Succeed, Fail, and Mislead
por: Michelucci, Umberto, et al.
Publicado: (2026)

Dataset-Driven Channel Masks in Transformers for Multivariate Time Series
por: Lee, Seunghan, et al.
Publicado: (2024)

ANT: Adaptive Noise Schedule for Time Series Diffusion Models
por: Lee, Seunghan, et al.
Publicado: (2024)

Soft Contrastive Learning for Time Series
por: Lee, Seunghan, et al.
Publicado: (2023)

Channel Normalization for Time Series Channel Identification
por: Lee, Seunghan, et al.
Publicado: (2025)

Learning to Embed Time Series Patches Independently
por: Lee, Seunghan, et al.
Publicado: (2023)

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
por: Frank, Gregory N.
Publicado: (2026)

When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking
por: Rehman, Mohammad Abdul, et al.
Publicado: (2025)

Deep Neural Networks via Complex Network Theory: a Perspective
por: La Malfa, Emanuele, et al.
Publicado: (2024)

Ascent Fails to Forget
por: Mavrothalassitis, Ioannis, et al.
Publicado: (2025)

Divergence-Suppressing Couplings for Rectified Flow
por: Min, Yimeng, et al.
Publicado: (2026)

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
por: Yang, Xiao, et al.
Publicado: (2025)

Lost in Transmission: When and Why LLMs Fail to Reason Globally
por: Schnabel, Tobias, et al.
Publicado: (2025)

Active Attacks: Red-teaming LLMs via Adaptive Environments
por: Yun, Taeyoung, et al.
Publicado: (2025)

Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
por: Roy, Saptarshi, et al.
Publicado: (2026)

Why Transformers Need Adam: A Hessian Perspective
por: Zhang, Yushun, et al.
Publicado: (2024)

Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
por: Yun, Taeyoung, et al.
Publicado: (2024)