Imagen de Portada

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	So, Shin, Lee, Kyelim, No, Albert
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition
por: Cho, Yoonjun, et al.
Publicado: (2025)

Mixture of Experts in Image Classification: What's the Sweet Spot?
por: Videau, Mathurin, et al.
Publicado: (2024)

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
por: Li, Ziheng, et al.
Publicado: (2025)

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
por: Liu, Zehao, et al.
Publicado: (2026)

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
por: Jeon, Dongjae, et al.
Publicado: (2024)

LoRA Is Slower Than You Think
por: Ko, Seokmin
Publicado: (2025)

Faster Adaptive Decentralized Learning Algorithms
por: Huang, Feihu, et al.
Publicado: (2024)

The Pitfalls of Memorization: When Memorization Hurts Generalization
por: Bayat, Reza, et al.
Publicado: (2024)

Memorization in Self-Supervised Learning Improves Downstream Generalization
por: Wang, Wenhao, et al.
Publicado: (2024)

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection
por: Butler, Jack, et al.
Publicado: (2025)

Faster Q-Learning Algorithms for Restless Bandits
por: Kakarapalli, Parvish, et al.
Publicado: (2024)

Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning
por: Nakashima, So, et al.
Publicado: (2024)

Faster Algorithms for Agnostically Learning Disjunctions and their Implications
por: Diakonikolas, Ilias, et al.
Publicado: (2025)

Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
por: Jiao, Yuchen, et al.
Publicado: (2025)

Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion
por: Werner, Blake, et al.
Publicado: (2025)

Prior Aware Memorization: An Efficient Metric for Distinguishing Memorization from Generalization in Large Language Models
por: Tiwari, Trishita, et al.
Publicado: (2026)

Generalization-Memorization Machines
por: Wang, Zhen, et al.
Publicado: (2022)

A Geometric Framework for Understanding Memorization in Generative Models
por: Ross, Brendan Leigh, et al.
Publicado: (2024)

A Faster $k$-means++ Algorithm
por: Liang, Jiehao, et al.
Publicado: (2022)

On the Dynamics & Transferability of Latent Generalization during Memorization
por: Ketha, Simran, et al.
Publicado: (2026)

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
por: Kim, Bumjun, et al.
Publicado: (2026)

Manifold Generalization Provably Proceeds Memorization in Diffusion Models
por: Shen, Zebang, et al.
Publicado: (2026)

SolidMark: Evaluating Image Memorization in Generative Models
por: Kriplani, Nicky, et al.
Publicado: (2025)

Generalization vs. Memorization in the Presence of Statistical Biases in Transformers
por: Mitros, John
Publicado: (2024)

Provable Separations between Memorization and Generalization in Diffusion Models
por: Ye, Zeqi, et al.
Publicado: (2025)

Memorization in In-Context Learning
por: Golchin, Shahriar, et al.
Publicado: (2024)

Generating Auxiliary Tasks with Reinforcement Learning
por: Goldfeder, Judah, et al.
Publicado: (2025)

System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
por: Lu, Linda, et al.
Publicado: (2025)

Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detection
por: Kang, Minseo, et al.
Publicado: (2026)

Generative Modeling of Weights: Generalization or Memorization?
por: Zeng, Boya, et al.
Publicado: (2025)

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation
por: Piché, Alexandre, et al.
Publicado: (2025)

Generalization and Memorization in Rectified Flow
por: Rao, Mingxing, et al.
Publicado: (2026)

Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
por: Li, Ziyue, et al.
Publicado: (2025)

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
por: Attias, Idan, et al.
Publicado: (2024)

Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
por: Kim, Gwangho, et al.
Publicado: (2026)

Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms
por: Schubert, Erich, et al.
Publicado: (2018)

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
por: Shi, Lianghe, et al.
Publicado: (2025)

Memorization Sinks: Isolating Memorization during LLM Training
por: Ghosal, Gaurav R., et al.
Publicado: (2025)

Transformers Learn Faster with Semantic Focus
por: Ram, Parikshit, et al.
Publicado: (2025)

Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders
por: Chen, Zhimin, et al.
Publicado: (2025)