How much data is sufficient to learn high-performing algorithms?
From MaRDI portal
Cites work
- scientific article; zbMATH DE number 6381703 (Why is no real title available?)
- scientific article; zbMATH DE number 5602305 (Why is no real title available?)
- scientific article; zbMATH DE number 3670138 (Why is no real title available?)
- A Computational Study of Search Strategies for Mixed Integer Programming
- A PAC Approach to Application-Specific Algorithm Selection
- Algorithmic Game Theory
- An Automatic Method of Solving Discrete Programming Problems
- Automated design of revenue-maximizing combinatorial auctions
- Convergence of stochastic processes
- Density and dimension
- Dispersion for data-driven algorithm design, online learning, and private optimization
- Efficiency and budget balance in general quasi-linear domains
- Efficient empirical revenue maximization in single-parameter auction environments
- Eigentaste: A constant time collaborative filtering algorithm
- Empirical hardness models, methodology and a case study on combinatorial auctions
- Generalization guarantees for multi-item profit maximization: pricing, auctions, and randomized mechanisms
- Guiding high-performance SAT solvers with unsat-core predictions
- How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design
- Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming
- Incentives in Teams
- Information-theoretic approaches to branching in search
- Learning multi-item auctions with (or without) samples
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- On the density of families of sets
- On the zeros of finite sums of exponential functions
- Pandora's box with correlations: learning and approximation
- Parameter advising for multiple sequence alignment
- Parametric inference for biological sequence analysis
- Parametric multiple sequence alignment and phylogeny construction
- Parametric optimization of sequence alignment
- Paramils: an automatic algorithm configuration framework
- Partition of Space
- Reinforcement learning for variable selection in a branch and bound algorithm
- Roberts' theorem with neutrality: a social welfare ordering approach
- SATzilla: portfolio-based algorithm selection for SAT
- SCIP: solving constraint integer programs
- Settling the sample complexity of single-parameter revenue maximization
- Some biological sequence metrics
- The RPR2 rounding technique for semidefinite programs
- The Sample Complexity of Up-to-ε Multi-dimensional Revenue Maximization
- The sample complexity of auctions with side information
- The sample complexity of revenue maximization
- The sample complexity of up-to- multi-dimensional revenue maximization
- Tropical geometry of statistical models
- Understanding machine learning. From theory to algorithms
This page was built for publication: How much data is sufficient to learn high-performing algorithms?
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6993546)
