Live briefing
Everything about Sample complexity
Attribute of machine learning models
The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Sample complexityA 5-minute orientation
- Skim a recent paper: Is Q-Learning Minimax Optimal? A Tight Sample Complexity AnalysisInfluential work since 2022
- Pick up a classic book: Computational Complexity of Counting and SamplingThe most-reprinted book on the subject
- Read the landmark paper: The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sampleCited 2,806 times
- Go sideways: Probably approximately correct learningA closely related topic
- Go sideways: Occam learningA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🏆 Landmark papers (most cited)
The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample
Improved Bounds on the Sample Complexity of Learning
The Sample Complexity of Multireference Alignment
Hamiltonian simulation with optimal sample complexity
Size-independent sample complexity of neural networks
Improving the sample complexity using global data
Measurement of climate complexity using sample entropy
The true sample complexity of active learning
🆕 Influential since 2022
Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
On the sample complexity of quantum Boltzmann machine learning
Sparse Group Lasso: Optimal Sample Complexity, Convergence Rate, and Statistical Inference
Settling the sample complexity of model-based offline reinforcement learning
📚 Books worth reading
Computational Complexity of Counting and SamplingIstvan Miklos · 2019- 📕Electron donor concentrations in sediments and sediment properties at the Agricultural Chemicals Team research site near New Providence, Iowa, 2006-07Bijesh Maharjan · 2013
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Probably approximately correct learning In computational learning theory, probably approximately correct (PAC) learning is a framework for mathematical analysis of machine learning. It was proposed…
- Occam learning In computational learning theory, Occam learning is a model of algorithmic learning where the objective of the learner is to output a succinct representation…
- Vapnik–Chervonenkis dimension In Vapnik–Chervonenkis theory, the Vapnik–Chervonenkis (VC) dimension is a measure of the size (capacity, complexity, expressive power, richness, or flexibility…
- Generalization error For supervised learning applications in machine learning and statistical learning theory, generalization error (also known as the out-of-sample error or…
- Distribution learning theory The distributional learning theory or learning of probability distribution is a framework in computational learning theory. It has been proposed from Michael…
- Error tolerance (PAC learning) In PAC learning, error tolerance refers to the ability of an algorithm to learn when the examples received have been corrupted in some way. In fact, this…
- Empirical risk minimization In statistical learning theory, the principle of empirical risk minimization defines a family of learning algorithms based on evaluating performance over…
- Stability (learning theory) Stability, also known as algorithmic stability, is a notion in computational learning theory of how a machine learning algorithm output is changed with…