Cover Image

A mathematical theory of balancing relational generalization and memorization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Luke, Lippl, Samuel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When does compositional structure yield compositional generalization? A kernel theory
by: Lippl, Samuel, et al.
Published: (2024)

Short window attention enables long-term memorization
by: Cabannes, Loïc, et al.
Published: (2025)

Math Takes Two: A test for emergent mathematical reasoning in communication
by: Cooper, Michael, et al.
Published: (2026)

Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
by: Lippl, Samuel, et al.
Published: (2025)

Deep sequence models tend to memorize geometrically; it is unclear why
by: Noroozizadeh, Shahriar, et al.
Published: (2025)

A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)
by: Taleb, Faiz, et al.
Published: (2025)

Self-rewarding correction for mathematical reasoning
by: Xiong, Wei, et al.
Published: (2025)

GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research
by: Howard, Luke
Published: (2025)

Putnam-like dataset summary: LLMs as mathematical competition contestants
by: Bieganowski, Bartosz, et al.
Published: (2025)

Differential learning kinetics govern the transition from memorization to generalization during in-context learning
by: Nguyen, Alex, et al.
Published: (2024)

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

Ratio law: mathematical descriptions for a universal relationship between AI performance and input samples
by: Kang, Boming, et al.
Published: (2024)

Time Matters: Scaling Laws for Any Budget
by: Inbar, Itay, et al.
Published: (2024)

Int2Int: a framework for mathematics with transformers
by: Charton, François
Published: (2025)

Linear Mode Connectivity in Sparse Neural Networks
by: McDermott, Luke, et al.
Published: (2023)

Reinforcement Learning with $ω$-Regular Objectives and Constraints
by: Wagner, Dominik, et al.
Published: (2025)

SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints
by: Wagner, Dominik, et al.
Published: (2025)

An explainable transformer circuit for compositional generalization
by: Tang, Cheng, et al.
Published: (2025)

Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning
by: Burega, Bradley, et al.
Published: (2024)

AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
by: Cho, Geonwoo, et al.
Published: (2025)

Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
by: Lippl, Samuel, et al.
Published: (2023)

All Random Features Representations are Equivalent
by: Sernau, Luke, et al.
Published: (2024)

Tucker Attention: A generalization of approximate attention mechanisms
by: Klein, Timon, et al.
Published: (2026)

In-Context Black-Box Optimization with Unreliable Feedback
by: Blumer, Nicolas Samuel, et al.
Published: (2026)

A Survey of State Representation Learning for Deep Reinforcement Learning
by: Echchahed, Ayoub, et al.
Published: (2025)

A multi-algorithm approach for operational human resources workload balancing in a last mile urban delivery system
by: Moreno-Saavedra, Luis M., et al.
Published: (2025)

On the Performance of Imputation Techniques for Missing Values on Healthcare Datasets
by: Joel, Luke Oluwaseye, et al.
Published: (2024)

MAD-SmaAt-GNet: A Multimodal Advection-Guided Neural Network for Precipitation Nowcasting
by: van Wonderen, Samuel, et al.
Published: (2026)

The Formalism-Implementation Gap in Reinforcement Learning Research
by: Castro, Pablo Samuel
Published: (2025)

Diffusion model for relational inference
by: Zheng, Shuhan, et al.
Published: (2024)

JaxUED: A simple and useable UED library in Jax
by: Coward, Samuel, et al.
Published: (2024)

Data-Aware Random Feature Kernel for Transformers
by: Farzam, Amirhossein, et al.
Published: (2026)

Feature maps for the Laplacian kernel and its generalizations
by: Ahir, Sudhendu, et al.
Published: (2025)

Towards a theory of out-of-distribution learning
by: Dey, Jayanta, et al.
Published: (2021)

Improving MoE Compute Efficiency by Composing Weight and Data Sparsity
by: Kilian, Maciej, et al.
Published: (2026)

Calibration in Deep Learning: A Survey of the State-of-the-Art
by: Wang, Cheng
Published: (2023)

Outcome-based Reinforcement Learning to Predict the Future
by: Turtel, Benjamin, et al.
Published: (2025)

Continuous Thought Machines
by: Darlow, Luke, et al.
Published: (2025)

Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization
by: Schapiro, Samuel, et al.
Published: (2024)

Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models
by: Junkin, Jared, et al.
Published: (2025)