Copertina

Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Yunzhe, Zou, Difan, Xu, Dong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
di: Hu, Yunzhe, et al.
Pubblicazione: (2024)

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
di: Smerkous, David, et al.
Pubblicazione: (2024)

HyperCore: Coreset Selection under Noise via Hypersphere Models
di: Moser, Brian B., et al.
Pubblicazione: (2025)

What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks
di: Chen, Xingwu, et al.
Pubblicazione: (2024)

How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
di: Chen, Xingwu, et al.
Pubblicazione: (2024)

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
di: Han, Yujin, et al.
Pubblicazione: (2024)

Physics-Informed Neural PDE Solvers via Spatio-Temporal MeanFlow
di: Bai, Hanru, et al.
Pubblicazione: (2026)

Model Unlearning via Sparse Autoencoder Subspace Guided Projections
di: Wang, Xu, et al.
Pubblicazione: (2025)

Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion
di: Chen, Rui, et al.
Pubblicazione: (2025)

Faster Sampling via Stochastic Gradient Proximal Sampler
di: Huang, Xunpeng, et al.
Pubblicazione: (2024)

Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion
di: Huang, Xunpeng, et al.
Pubblicazione: (2025)

Uncertainty Estimation via Hyperspherical Confidence Mapping
di: Choi, Eunseo, et al.
Pubblicazione: (2026)

nGPT: Normalized Transformer with Representation Learning on the Hypersphere
di: Loshchilov, Ilya, et al.
Pubblicazione: (2024)

Structured Role-Aware Policy Optimization for Multimodal Reasoning
di: Jiang, Bingqing, et al.
Pubblicazione: (2026)

On the Memorization of Consistency Distillation for Diffusion Models
di: Jiang, Bingqing, et al.
Pubblicazione: (2026)

Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
di: Chen, Xingwu, et al.
Pubblicazione: (2025)

Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
di: Wang, Xu, et al.
Pubblicazione: (2025)

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
di: Bai, Hanru, et al.
Pubblicazione: (2025)

The Implicit Bias of Adam on Separable Data
di: Zhang, Chenyang, et al.
Pubblicazione: (2024)

Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems
di: Su, Junwei, et al.
Pubblicazione: (2024)

On the Limitation and Experience Replay for GNNs in Continual Learning
di: Su, Junwei, et al.
Pubblicazione: (2023)

The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
di: Li, Jichu, et al.
Pubblicazione: (2026)

PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
di: Su, Junwei, et al.
Pubblicazione: (2024)

A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
di: Xie, Chengxing, et al.
Pubblicazione: (2024)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2026)

Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
di: Huang, Xunpeng, et al.
Pubblicazione: (2024)

HYPO: Hyperspherical Out-of-Distribution Generalization
di: Bai, Haoyue, et al.
Pubblicazione: (2024)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
di: Wang, Xu, et al.
Pubblicazione: (2025)

Capturing Conditional Dependence via Auto-regressive Diffusion Models
di: Huang, Xunpeng, et al.
Pubblicazione: (2025)

Hyperspherical Normalization for Scalable Deep Reinforcement Learning
di: Lee, Hojoon, et al.
Pubblicazione: (2025)

An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
di: Huang, Xunpeng, et al.
Pubblicazione: (2024)

Learning under Quantization for High-Dimensional Linear Regression
di: Zhang, Dechen, et al.
Pubblicazione: (2025)

Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
di: Chen, Xingwu, et al.
Pubblicazione: (2025)

A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
di: Tang, Xuan, et al.
Pubblicazione: (2025)

On the Robustness of Transformers against Context Hijacking for Linear Classification
di: Li, Tianle, et al.
Pubblicazione: (2025)

Hyperspherical Forward-Forward with Prototypical Representations
di: Sarode, Shalini, et al.
Pubblicazione: (2026)

F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
di: Zhang, Hangwei, et al.
Pubblicazione: (2025)

Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks
di: Zhang, Chenyang, et al.
Pubblicazione: (2025)

Towards Robust Graph Incremental Learning on Evolving Graphs
di: Su, Junwei, et al.
Pubblicazione: (2024)

On the Benefits of Over-parameterization for Out-of-Distribution Generalization
di: Hao, Yifan, et al.
Pubblicazione: (2024)