Sample Complexity
Overview
Sample complexity quantifies the data or oracle access needed to achieve a specified accuracy and confidence in tasks such as PAC learning, estimation, hypothesis testing, system identification, and generative sampling. Researchers derive upper and lower bounds using tools such as VC and Rademacher complexity, information-theoretic arguments, minimax analysis, and adaptive sampling algorithms. A central theme is how structure—sparsity, low intrinsic dimension, symmetry, smoothness, or prior knowledge—can reduce data needs, while noise, distribution shift, robustness, and limited feedback can raise them. Matching bounds are known in many settings, but guarantees can change sharply with the task, assumptions, and resource being counted, so translating theory to practical data requirements remains an open challenge.
Latest papers
110 papers15 papers in the last four weeks, down 21% on the four weeks before. 0.1% of all new papers.
Adversarially Robust PAC Learning with Optimal VC Rates
Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start
Learning CNF Formulas from Uniform Random Solutions: Near-Tight Sample Complexity for Valiant's Algorithm
Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification
Tight Sampling Complexity with Stochastic Gradient Oracles in Fixed Dimensions
Bandit Multiclass PAC Learning: Structural Baselines and a Confidence Direct Sum
Learning to Price with Persuasion
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
Sample Complexity of Multicalibration for Multilevel Properties
Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation
Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling
Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories
The Tractability Landscape of Sampling with Inexact Scores
On the Limits of Sampling-Based Reachability: Geometry, Dynamics, and Sample Complexity
Tight Sample Bounds for Renyi and Min-Entropy Estimation
From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP
Data-Efficient Deep Learning: Empirical Guidelines for Training Set Size Estimation in Inertial Sensor Classification
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
active'' component, which keeps the data-dependent low-dimensional statistics, and a lazy'' component, which resamples the entropy-dominated directions from the prior. Thus the infinite-width mean-field limit gives a clean analytic description of learning without introducing spurious width-dependent generalization power.