Get started
Keyword

hypothesis classes

Description: Sets of candidate predictive functions considered by learning algorithms, used to analyze learnability and generalization in machine learning.
OpenAlex ID: keywords/hypothesis-classes
The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information
2007 · John Langford, Tong Zhang · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 426
Three Approaches for Personalization with Applications to Federated Learning
2020 · Mansour, Yishay, Mohri, Mehryar, et al. · arXiv (Cornell University) · 337
PDF
The Epoch-Greedy algorithm for contextual multi-armed bandits
2007 · John Langford, Tong Zhang · 307
Two faces of active learning
2010 · Sanjoy Dasgupta · Theoretical Computer Science · 248
PDF
A General Agnostic Active Learning Algorithm.
2008 · Sanjoy Dasgupta, Daniel Hsu, et al. · 207
Relating Data Compression and Learnability
2003 · Nick Littlestone, Manfred K. Warmuth · 203
Statistical Learning Theory: Models, Concepts, and Results
2011 · Ulrike von Luxburg, Bernhard Schölkopf · Handbook of the history of logic · 189
On the difficulty of approximately maximizing agreements
2003 · Shai Ben-David, Nadav Eiron, et al. · Journal of Computer and System Sciences · 134
PDF
Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.
2008 · Shai Ben-David, Tyler Lu, et al. · Conference on Learning Theory · 102
A decision-theoretic extension of stochastic complexity and its applications to learning
1998 · K. Yamanishi · IEEE Transactions on Information Theory · 89
Generalizing the PAC model: sample size bounds from metric dimension-based uniform convergence results
1989 · D. Haussler · Annual Symposium on Foundations of Computer Science · 68
From average case complexity to improper learning complexity
2014 · Amit Daniely, Nati Linial, et al. · ACM Symposium on Theory of Computing (STOC) · 61
Computational Learning Theory
1998 · Sally Goldman · Chapman & Hall/CRC applied algorithms and data structures series · 60
VC Classes are Adversarially Robustly Learnable, but Only Improperly
2019 · Montasser, Omar, Hanneke, Steve, et al. · arXiv (Cornell University) · 57
PDF
Improved Guarantees for Learning via Similarity Functions
2018 · Maria-Florina Balcan, Avrim Blum, et al. · Figshare · 46
PDF
In-Context Learning Creates Task Vectors
2023 · Roee Hendel, Mor Geva, et al. · 43
PDF
Optimistic Rates for Learning with a Smooth Loss
2010 · Srebro, Nathan, Sridharan, Karthik, et al. · arXiv (Cornell University) · 40
PDF
Differentially Private Testing of Identity and Closeness of Discrete Distributions
2017 · Acharya, Jayadev, Sun, Ziteng, et al. · arXiv (Cornell University) · 38
PDF
Experience-efficient learning in associative bandit problems
2006 · Alexander L. Strehl, Chris Mesterharm, et al. · International Conference on Machine Learning · 38
Optimal Learners for Multiclass Problems
2014 · Daniely, Amit, Shalev-Shwartz, Shai · arXiv (Cornell University) · 36
PDF
Efficient Exploration and Value Function Generalization in Deterministic Systems
2013 · Zheng Wen, Benjamin Van Roy · 36
Why averaging classifiers can protect against overfitting.
2001 · Yoav Freund, Yishay Mansour, et al. · 35
Active Learning for Smooth Problems.
2009 · Eric Friedman · 34
Structured Prediction Theory Based on Factor Graph Complexity
2016 · Cortes, Corinna, Mohri, Mehryar, et al. · arXiv (Cornell University) · 32
PDF
Sample Complexity of Automated Mechanism Design
2016 · Balcan, Maria-Florina, Sandholm, Tuomas, et al. · arXiv (Cornell University) · 31
PDF
Works count: 250
Citation count: 3,684
Year
Topic
Type