Image de couverture de livre

How Much Data Is Enough? Uniform Convergence Bounds for Generative & Vision-Language Models under Low-Dimensional Structure

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Thompson, Paul M.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function
par: Thompson, Paul M.
Publié: (2026)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
par: Zhai, Zhiyuan, et autres
Publié: (2026)

Do Large Language Models Know How Much They Know?
par: Prato, Gabriele, et autres
Publié: (2025)

How Much Can We Forget about Data Contamination?
par: Bordt, Sebastian, et autres
Publié: (2024)

BertaQA: How Much Do Language Models Know About Local Culture?
par: Etxaniz, Julen, et autres
Publié: (2024)

Robust Subspace-Constrained Quadratic Models for Low-Dimensional Structure Learning
par: Zhai, Zheng, et autres
Publié: (2026)

Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees
par: Wang, Cangqing, et autres
Publié: (2024)

When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate
par: Forest, Florent, et autres
Publié: (2025)

How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness
par: Rathore, Darshita, et autres
Publié: (2025)

Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
par: Madras, David, et autres
Publié: (2025)

Assessing Generative Models for Structured Data
par: Cannon, Reilly, et autres
Publié: (2025)

How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
par: Park, Sumin, et autres
Publié: (2025)

Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
par: Yang, Shenzhi, et autres
Publié: (2025)

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
par: Deb, Rohan, et autres
Publié: (2025)

How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots
par: Yu, Hang, et autres
Publié: (2024)

Non-Uniform Class-Wise Coreset Selection for Vision Model Fine-tuning
par: Zhang, Hanyu, et autres
Publié: (2025)

Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees
par: Schotthöfer, Steffen, et autres
Publié: (2024)

Screening Is Enough
par: Nakanishi, Ken M.
Publié: (2026)

Tight Lower Bounds and Improved Convergence in Performative Prediction
par: Khorsandi, Pedram, et autres
Publié: (2024)

Towards General Continuous Memory for Vision-Language Models
par: Wu, Wenyi, et autres
Publié: (2025)

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
par: Wang, Yuqing, et autres
Publié: (2025)

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
par: Dabas, Mahavir, et autres
Publié: (2025)

A Fine-Grained Understanding of Uniform Convergence for Halfspaces
par: Kontorovich, Aryeh, et autres
Publié: (2026)

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
par: Li, Lin, et autres
Publié: (2024)

Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning
par: Lee, Younghwan, et autres
Publié: (2025)

Convergent Evolution: How Different Language Models Learn Similar Number Representations
par: Fu, Deqing, et autres
Publié: (2026)

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
par: Li, Gen, et autres
Publié: (2024)

What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction
par: Li, Lingbo, et autres
Publié: (2025)

Sparse is Enough in Fine-tuning Pre-trained Large Language Models
par: Song, Weixi, et autres
Publié: (2023)

Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
par: Ciaperoni, Martino, et autres
Publié: (2026)

Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling
par: Ulm, Jannek, et autres
Publié: (2025)

LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)
par: Li, Guozhong, et autres
Publié: (2025)

Nonlinearity, Feedback and Uniform Consistency in Causal Structural Learning
par: Wang, Shuyan
Publié: (2023)

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
par: Balef, Amir Rezaei, et autres
Publié: (2026)

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
par: Su, Jiayuan, et autres
Publié: (2024)

Softmax is not Enough (for Adaptive Conformal Classification)
par: Attar, Navid Akhavan, et autres
Publié: (2026)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
par: Sernau, Luke
Publié: (2024)

Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
par: Wang, Hongjun, et autres
Publié: (2026)

When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
par: Mustaqim, S. M., et autres
Publié: (2025)

Discovering Association Rules in High-Dimensional Small Tabular Data
par: Karabulut, Erkan, et autres
Publié: (2025)