Cover Image

Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rubin, Noa, Davidovich, Orit, Ringel, Zohar
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers
by: Davidovich, Orit, et al.
Published: (2026)

Grokking as a First Order Phase Transition in Two Layer Networks
by: Rubin, Noa, et al.
Published: (2023)

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
by: Rubin, Noa, et al.
Published: (2025)

Applications of Statistical Field Theory in Deep Learning
by: Ringel, Zohar, et al.
Published: (2025)

Demystifying Spectral Bias on Real-World Data
by: Lavie, Itay, et al.
Published: (2024)

Heuristics for Combinatorial Optimization via Value-based Reinforcement Learning: A Unified Framework and Analysis
by: Davidovich, Orit, et al.
Published: (2025)

Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems
by: Megiddo, Nimrod, et al.
Published: (2025)

Towards Understanding Inductive Bias in Transformers: A View From Infinity
by: Lavie, Itay, et al.
Published: (2024)

An Analysis and Mitigation of the Reversal Curse
by: Lv, Ang, et al.
Published: (2023)

Learning a Continue-Thinking Token for Enhanced Test-Time Scaling
by: Ringel, Liran, et al.
Published: (2025)

Wilsonian Renormalization of Neural Network Gaussian Processes
by: Howard, Jessica N., et al.
Published: (2024)

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
by: Xia, Song, et al.
Published: (2024)

Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
by: Lu, Chenbei, et al.
Published: (2024)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2025)

OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
by: Suri, Sanah, et al.
Published: (2026)

Understanding the Curse of Unrolling
by: Mehmood, Sheheryar, et al.
Published: (2026)

Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling
by: Chen, Yu-hsuan, et al.
Published: (2025)

The Curse of Diversity in Ensemble-Based Exploration
by: Lin, Zhixuan, et al.
Published: (2024)

On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
by: Wang, Yiming, et al.
Published: (2026)

Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
by: Guo, Qingyan, et al.
Published: (2024)

Separable DeepONet: Breaking the Curse of Dimensionality in Physics-Informed Machine Learning
by: Mandl, Luis, et al.
Published: (2024)

Semi-Supervised Risk Control via Prediction-Powered Inference
by: Einbinder, Bat-Sheva, et al.
Published: (2024)

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
by: Longpre, Shayne, et al.
Published: (2025)

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
by: Jacot, Arthur, et al.
Published: (2024)

The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
by: Kitouni, Ouail, et al.
Published: (2024)

Mixture of Experts Softens the Curse of Dimensionality in Operator Learning
by: Kratsios, Anastasis, et al.
Published: (2024)

Curse of Dimensionality in Neural Network Optimization
by: Na, Sanghoon, et al.
Published: (2025)

The Blessing and Curse of Dimensionality in Safety Alignment
by: Teo, Rachel S. Y., et al.
Published: (2025)

The Curse of Depth in Large Language Models
by: Sun, Wenfang, et al.
Published: (2025)

Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
by: Wei, Qi, et al.
Published: (2024)

Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum
by: Kumar, Navdeep, et al.
Published: (2026)

Provable Target Sample Complexity Improvements as Pre-Trained Models Scale
by: Fukuchi, Kazuto, et al.
Published: (2026)

CNNs Avoid Curse of Dimensionality by Learning on Patches
by: Madala, Vamshi C., et al.
Published: (2022)

The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning
by: Block, Adam, et al.
Published: (2023)

On the Sample Complexity of Learning for Blind Inverse Problems
by: Buskulic, Nathan, et al.
Published: (2025)

The Optimal Sample Complexity of Multiclass and List Learning
by: Pabbaraju, Chirag
Published: (2026)

Settling the Sample Complexity of Online Reinforcement Learning
by: Zhang, Zihan, et al.
Published: (2023)

From Words to Amino Acids: Does the Curse of Depth Persist?
by: Siji, Aleena, et al.
Published: (2026)

Feature-Wise Mixing for Mitigating Contextual Bias in Predictive Supervised Learning
by: Tomar, Yash Vardhan
Published: (2025)

Dispelling the Curse of Singularities in Neural Network Optimizations
by: Cao, Hengjie, et al.
Published: (2026)