Image de couverture de livre

A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nakada, Ryumei, Ji, Wenlong, Cai, Tianxi, Zou, James, Zhang, Linjun
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Contrastive Learning on Multimodal Analysis of Electronic Health Records
par: Cai, Tianxi, et autres
Publié: (2024)

Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
par: Zhang, Zhe, et autres
Publié: (2024)

Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
par: Nakada, Ryumei, et autres
Publié: (2024)

Residual Feature Integration is Sufficient to Prevent Negative Transfer
par: Xu, Yichen, et autres
Publié: (2025)

Contrastive Network Representation Learning
par: Dong, Zihan, et autres
Publié: (2025)

Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
par: Huang, Alyssa, et autres
Publié: (2023)

PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
par: Zhong, Yibo, et autres
Publié: (2024)

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
par: Yang, Xinyu, et autres
Publié: (2024)

FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee
par: Li, Puheng, et autres
Publié: (2022)

Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
par: Ye, Haotian, et autres
Publié: (2022)

Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL
par: Tong, Xuhan, et autres
Publié: (2026)

Prompt Engineering a Prompt Engineer
par: Ye, Qinyuan, et autres
Publié: (2023)

Alternating Training-based Label Smoothing Enhances Prompt Generalization
par: Chen, Yang, et autres
Publié: (2025)

Prompting a Pretrained Transformer Can Be a Universal Approximator
par: Petrov, Aleksandar, et autres
Publié: (2024)

Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks
par: Yang, Guangrui, et autres
Publié: (2024)

Scaling Laws for the Value of Individual Data Points in Machine Learning
par: Covert, Ian, et autres
Publié: (2024)

Memory Limitations of Prompt Tuning in Transformers
par: Meyer, Maxime, et autres
Publié: (2025)

A Statistical Framework for Alignment with Biased AI Feedback
par: Xia, Xintao, et autres
Publié: (2026)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
par: Khan, Imran
Publié: (2025)

Initialization Method for Factorization Machine Based on Low-Rank Approximation for Constructing a Corrected Approximate Ising Model
par: Seki, Yuya, et autres
Publié: (2024)

A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
par: Cai, Yinpeng, et autres
Publié: (2025)

Molecule Design by Latent Prompt Transformer
par: Kong, Deqian, et autres
Publié: (2023)

Molecule Design by Latent Prompt Transformer
par: Kong, Deqian, et autres
Publié: (2024)

Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
par: Deng, Wenlong, et autres
Publié: (2023)

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction
par: Ye, Zesheng, et autres
Publié: (2025)

Statistical Inference for Differentially Private Stochastic Gradient Descent
par: Xia, Xintao, et autres
Publié: (2025)

Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction
par: Zou, Tao, et autres
Publié: (2025)

PromptWizard: Task-Aware Prompt Optimization Framework
par: Agarwal, Eshaan, et autres
Publié: (2024)

From Prompting to Alignment: A Generative Framework for Query Recommendation
par: Min, Erxue, et autres
Publié: (2025)

A Survey of Automatic Prompt Engineering: An Optimization Perspective
par: Li, Wenwu, et autres
Publié: (2025)

Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineering
par: Sarukkai, Vishnu, et autres
Publié: (2025)

Prompt Tuning Decision Transformers with Structured and Scalable Bandits
par: Rietz, Finn, et autres
Publié: (2025)

Prompt Design and Engineering: Introduction and Advanced Methods
par: Amatriain, Xavier
Publié: (2024)

Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
par: Yashwanth, M, et autres
Publié: (2025)

Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
par: Ding, Meng, et autres
Publié: (2024)

RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents
par: Chen, Weizhe, et autres
Publié: (2024)

Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning
par: Ruksana, Shiek, et autres
Publié: (2026)

MGDA Converges under Generalized Smoothness, Provably
par: Zhang, Qi, et autres
Publié: (2024)

Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions
par: Epasto, Alessandro, et autres
Publié: (2020)

Consensus Knowledge Graph Learning via Multi-view Sparse Low Rank Block Model
par: Cai, Tianxi, et autres
Publié: (2022)