Copertina

Scaling Laws and In-Context Learning: A Unified Theoretical Framework

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mehta, Sushant, Gupta, Ishan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When Are Learning Biases Equivalent? A Unifying Framework for Fairness, Robustness, and Distribution Shift
di: Mehta, Sushant
Pubblicazione: (2025)

Beyond Surface-Level Similarity: Hierarchical Contamination Detection for Synthetic Training Data in Foundation Models
di: Mehta, Sushant
Pubblicazione: (2025)

Information-Theoretic Foundations for Neural Scaling Laws
di: Jeon, Hong Jun, et al.
Pubblicazione: (2024)

Optimal Scaling Laws for Efficiency Gains in a Theoretical Transformer-Augmented Sectional MoE Framework
di: Sane, Soham
Pubblicazione: (2025)

Unifying Learning Dynamics and Generalization in Transformers Scaling Law
di: Yang, Chiwun
Pubblicazione: (2025)

A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
di: Zhang, Miao, et al.
Pubblicazione: (2025)

Theoretical Foundations of Scaling Law in Familial Models
di: Song, Huan, et al.
Pubblicazione: (2025)

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning
di: Wu, Xiaojun, et al.
Pubblicazione: (2025)

A Unified Framework for Model Editing
di: Gupta, Akshat, et al.
Pubblicazione: (2024)

Predicting Task Performance with Context-aware Scaling Laws
di: Montgomery, Kyle, et al.
Pubblicazione: (2025)

Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers
di: Mittal, Sarthak, et al.
Pubblicazione: (2025)

EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments
di: Mehta, Sushant, et al.
Pubblicazione: (2026)

Federated Learning Framework via Distributed Mutual Learning
di: Gupta, Yash
Pubblicazione: (2025)

Scaling Laws for Data-Efficient Visual Transfer Learning
di: Yang, Wenxuan, et al.
Pubblicazione: (2025)

Scaling Laws for Imitation Learning in Single-Agent Games
di: Tuyls, Jens, et al.
Pubblicazione: (2023)

A Unifying Framework for Learning Argumentation Semantics
di: Mileva, Zlatina, et al.
Pubblicazione: (2023)

EDGE: A Theoretical Framework for Misconception-Aware Adaptive Learning
di: Verma, Ananda Prakash
Pubblicazione: (2025)

Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems
di: Mehta, Sushant
Pubblicazione: (2025)

Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
di: Gu, Zhengyao, et al.
Pubblicazione: (2025)

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
di: Gupta, Karan, et al.
Pubblicazione: (2026)

A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
di: Song, Bingqing, et al.
Pubblicazione: (2025)

A Unified Framework for Heterogeneous Semi-supervised Learning
di: Heidari, Marzi, et al.
Pubblicazione: (2025)

A Unified Invariant Learning Framework for Graph Classification
di: Sui, Yongduo, et al.
Pubblicazione: (2025)

Mirror Learning: A Unifying Framework of Policy Optimisation
di: Kuba, Jakub Grudzien, et al.
Pubblicazione: (2022)

Operator-Theoretic Framework for Gradient-Free Federated Learning
di: Kumar, Mohit, et al.
Pubblicazione: (2025)

Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
di: Yao, Xinhao, et al.
Pubblicazione: (2024)

CacheFormer: High Attention-Based Segment Caching
di: Singh, Sushant, et al.
Pubblicazione: (2025)

Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
di: Tian, Yuandong
Pubblicazione: (2025)

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
di: Ma, Qian, et al.
Pubblicazione: (2024)

Scaling Law with Learning Rate Annealing
di: Tissue, Howe, et al.
Pubblicazione: (2024)

A Unified Framework for Neural Computation and Learning Over Time
di: Melacci, Stefano, et al.
Pubblicazione: (2024)

A Unified Framework for Human-Allied Learning of Probabilistic Circuits
di: Karanam, Athresh, et al.
Pubblicazione: (2024)

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
di: Chen, Qi, et al.
Pubblicazione: (2025)

KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
di: Singh, Vaibhav, et al.
Pubblicazione: (2025)

Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting
di: Cheng, Ran
Pubblicazione: (2026)

On Implications of Scaling Laws on Feature Superposition
di: Katta, Pavan
Pubblicazione: (2024)

Scaling Law Hypothesis for Multimodal Model
di: Sun, Qingyun, et al.
Pubblicazione: (2024)

Towards Neural Scaling Laws on Graphs
di: Liu, Jingzhe, et al.
Pubblicazione: (2024)

On the Optimizer Dependence of Neural Scaling Laws
di: Ramani, Vansh, et al.
Pubblicazione: (2026)

Scaling Law for Time Series Forecasting
di: Shi, Jingzhe, et al.
Pubblicazione: (2024)