Copertina

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Wendao, Zhang, Fangqing, Zhang, Haihan, Fang, Cong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimal Algorithms in Linear Regression under Covariate Shift: On the Importance of Precondition
di: Liu, Yuanshi, et al.
Pubblicazione: (2025)

Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression
di: Ding, Shihong, et al.
Pubblicazione: (2025)

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

Scaling Laws for Precision in High-Dimensional Linear Regression
di: Zhang, Dechen, et al.
Pubblicazione: (2026)

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning
di: Ge, Haosen, et al.
Pubblicazione: (2025)

DP-LET: An Efficient Spatio-Temporal Network Traffic Prediction Framework
di: Wang, Xintong, et al.
Pubblicazione: (2025)

Grokking in Linear Models for Logistic Regression
di: Das, Nataraj, et al.
Pubblicazione: (2026)

Learning Curves of Stochastic Gradient Descent in Kernel Regression
di: Zhang, Haihan, et al.
Pubblicazione: (2025)

Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
di: Cao, Yi, et al.
Pubblicazione: (2026)

Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework
di: Zhang, Qingyue, et al.
Pubblicazione: (2026)

CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
di: Liu, Yan, et al.
Pubblicazione: (2024)

Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation
di: Gan, Chunjing, et al.
Pubblicazione: (2023)

MVKTrans: Multi-View Knowledge Transfer for Robust Multiomics Classification
di: Cong, Shan, et al.
Pubblicazione: (2024)

Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
di: Ko, Sung Moon, et al.
Pubblicazione: (2023)

Deconstructing What Makes a Good Optimizer for Language Models
di: Zhao, Rosie, et al.
Pubblicazione: (2024)

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
di: Wu, Zhoutong, et al.
Pubblicazione: (2025)

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection
di: Zhang, Yiqun, et al.
Pubblicazione: (2026)

What Makes a Good Diffusion Planner for Decision Making?
di: Lu, Haofei, et al.
Pubblicazione: (2025)

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
di: Balasubramanian, Rishab, 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)

A Visualization for Comparative Analysis of Regression Models
di: Mountasir, Nassime, et al.
Pubblicazione: (2026)

Highly Imbalanced Regression with Tabular Data in SEP and Other Applications
di: Moukpe, Josias K., et al.
Pubblicazione: (2025)

A Hybrid Framework for Spatial Interpolation: Merging Data-driven with Domain Knowledge
di: Zhang, Cong, et al.
Pubblicazione: (2024)

In-Context Learning in Linear vs. Quadratic Attention Models: An Empirical Study on Regression Tasks
di: Goel, Ayush, et al.
Pubblicazione: (2026)

Superiority of Multi-Head Attention in In-Context Linear Regression
di: Cui, Yingqian, et al.
Pubblicazione: (2024)

Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
di: Ding, Zifeng, et al.
Pubblicazione: (2023)

MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
di: Xie, Luyuan, et al.
Pubblicazione: (2024)

Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
di: Zuo, Yifei, et al.
Pubblicazione: (2025)

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models
di: He, Chen, et al.
Pubblicazione: (2025)

Learning Robust Spectral Dynamics for Temporal Domain Generalization
di: Yu, En, et al.
Pubblicazione: (2025)

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
di: Kim, Kihyun, et al.
Pubblicazione: (2024)

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
di: Zhang, Qingyue, et al.
Pubblicazione: (2025)

Spectral Adapter: Fine-Tuning in Spectral Space
di: Zhang, Fangzhao, et al.
Pubblicazione: (2024)

Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework
di: Liu, Lingyuan, et al.
Pubblicazione: (2025)

Automatic Piecewise Linear Regression for Predicting Student Learning Satisfaction
di: Choi, Haemin, et al.
Pubblicazione: (2025)

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning
di: Jia, Yaning, et al.
Pubblicazione: (2025)

Ranking over Regression for Bayesian Optimization and Molecule Selection
di: Tom, Gary, et al.
Pubblicazione: (2024)

Position: What Can Large Language Models Tell Us about Time Series Analysis
di: Jin, Ming, et al.
Pubblicazione: (2024)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
di: Chou, Yuhong, et al.
Pubblicazione: (2024)

A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models
di: Xu, Jingjing, et al.
Pubblicazione: (2025)