Hypothesis Class

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 25

All topics

Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs
Sep 27, 2026Gon Buzaglo, Elad HazanLearning-Augmented Algorithms Hypothesis Class
Department of Computer Science, Princeton University · Google DeepMind
On the Sample Complexity of Active Learning with Membership Queries
Sep 23, 2026Ganghua Wang, Shaddin DughmiPool-Based Active Learning Active Learning
Department of Mathematics University of Arizona · Department of Computer Science University of Southern California
The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs
Sep 17, 2026Paul Biberstein, Joseph Devietti, Mayur NaikCuda Bug
University of Pennsylvania Philadelphia, PA, USA
Learning the Geometry of Admissible Hypotheses through Inductive Bias in Training Distributions
Aug 31, 2026James Crowley, Faez Ahmed, Anton van BeekPartial Differential Equations Hypothesis Class
School of Mechanical and Material Engineering University College Dublin · Department of Mechanical Engineering Massachusets Institute of Technology
Defensive Boosting for Online Probabilistic Forecasting
Aug 13, 2026Georgy Noarov, Aaron RothProbabilistic Forecasting Learning-Augmented Algorithms
Constrained Learning with Universally Learnable Concept Classes
Aug 9, 2026Herlock SeyedAbolfazl Rahimi, Spyridon Pougkakiotis, Dionysis KalogeriasLearnability Uncoupled Learning
1Yale University · 2King’s College London
Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning
Aug 3, 2026Irene TsaparaHypothesis Class Atoms
National University, San Diego, United States
Fast Rates for Swap-Agnostic Learning of Proper Losses
Jul 30, 2026Princewill OkoroaforLearning-Augmented Algorithms Optimal Sample Complexity
Harvard University
Hierarchical Domain Generalization
Jul 17, 2026Chenxiao Yang, Zhiyuan Li, Shai Ben-David +1Multimodal Domain Generalization Hypothesis Class
Toyota Technological Institute at Chicago · University of Waterloo
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Jun 28, 2026Şuayp Talha Kocabay, Talha Rüzgar Akkuş, Kerem YalçınSymbolic Regression Sample Complexity
Independent Researcher · TÜBİTAK Science High School
Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces
Jun 13, 2026Binyamin Perets, Shie MannorFalse Discovery Rate Two-Sample Testing
Technion – Israel Institute of Technology · NVIDIA
A Complexity Measure for Active Learning in Multi-group Mean Estimation
Jun 12, 2026Abdellah Aznag, Rachel Cummings, Adam N. ElmachtoubActive Learning Optimal Sample Complexity
Department of Industrial Engineering and Operations Research & Data Science Institute, Columbia University
Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
Jun 12, 2026Li Xia, Baoxun WangModel Discovery Discovery
School of Economics and Management, Tsinghua University · Platform & Content Group, Tencent
Contemporary AI lacks the imagination to diverge or negate in science
Jun 6, 2026Honglin Bao, Siyang Wu, Xiao Liu +3Scientific Discovery Artificial Intelligence Evaluation
Data Science Institute, University of Chicago · Knowledge Lab, University of Chicago
Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces
Jun 5, 2026Laura Wynter, Nirvik Sahoo, Paul GriffinLegal Reasoning Tasks Legal Domain
School of Computing and Information Systems Singapore Management University Singapore
How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?
May 31, 2026Michael Benedikt, Alessio MansuttiHypothesis Class Tractability
University of Oxford, UK · IMDEA Software Institute, Spain
The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity
May 28, 2026Mikael Møller Høgsgaard, Kasper Green Larsen, Liang-Yu ZouStochastic Interpolants Learnability
Department of Computer Science, Aarhus University, Aarhus, Denmark · Department of Statistics, University of Oxford, Oxford, United Kingdom
Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels
May 17, 2026Binyamin Perets, Shie MannorFalse Discovery Rate Reproducing Kernel Hilbert Spaces
Technion – Israel Institute of Technology · NVIDIA
Strategic PAC Learnability via Geometric Definability
May 13, 2026Yuval Filmus, Shay Moran, Elizaveta Nesterova +2Hypothesis Class Learnability
Faculty of Mathematics, Technion – Israel Institute of Technology. · Faculty of Computer Science, Technion – Israel Institute of Technology. · Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology. +1
A Survey on Data-Dependent Worst-Case Generalization Bounds
May 13, 2026Hubert Leroux, Jean Marcus, Julien RogerGeneralization Bounds Overparameterization
´Ecole polytechnique Palaiseau, France
CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction
May 8, 2026Mengran Li, Bo Li, Jiaying Wang +7Virtual Cell Single-Cell Perturbation Prediction
Center for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation (HKISI)
Ratio-based Loss Functions
May 7, 2026Lena Helgerth, Andreas ChristmannLoss Function Lipschitz Continuity
Department of Mathematics, University of Bayreuth, Chair of Stochastics and Machine Learning, 95440 Bayreuth, Germany
Realizable Bayes-Consistency for General Metric Losses
May 5, 2026Dan Tsir Cohen, Steve Hanneke, Aryeh KontorovichHypothesis Class Pac-Bayesian Theory
1Ben-Gurion University of the Negev · 2Purdue University, USA.
The Optimal Sample Complexity of Multiclass and List Learning
Apr 27, 2026Chirag PabbarajuMulticlass Classification Optimal Sample Complexity
Stanford University
Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents
Apr 21, 2026John Alderete, Sebastian Benthal, Connie Xu +1Agentic Reasoning Hypothesis-Driven Model Expansion
Amigo AI · Simon Fraser University · International Computer Science Institute

Sep 27, 2026, cs.LGJ/K move · Enter open · S save

Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs

Gon Buzaglo, Elad Hazan

Department of Computer Science, Princeton University · Google DeepMind

Learning-Augmented Algorithms Hypothesis Class \Widetilde{\Mathcal{O}}(\Sqrt{T})$ Regret Adversarial Robustness Optimistic Follow-The-Regularized-Leader Stochastic

Open paper AskPDF arXiv

We consider contextual binary prediction with i.i.d. contexts from an unknown distribution and adaptively chosen losses. We show that a simple Follow-the-Perturbed-Leader algorithm with Gaussian perturbation for each observed context achieves the optimal

\widetilde O(\sqrt{T\log N})

expected regret for a class of

N

experts, while requiring one optimization-oracle call per round and no explicit enumeration of the class. For an infinite hypothesis class

\mathcal H

, the algorithm attains

\widetilde O(\sqrt{T\operatorname{VC}(\mathcal H)})

regret. This resolves an open problem posed by Lazaric and Munos (2012), showing that hybrid classification is computationally as easy as statistical learning.

Momentum

Related topics

Latest papers 25