Learning discrete distributions from untrusted batches
From MaRDI portal
Recommendations
Cites work
- A new approach to the planted clique problem
- Bernstein polynomials and learning theory
- Codes based on inaccurate source probabilities
- Estimating the unseen, an \(n/\log(n)\)-sample estimator for entropy and support size, shown optimal via new CLTs
- scientific article; zbMATH DE number 3954047 (Why is no real title available?)
- scientific article; zbMATH DE number 5485581 (Why is no real title available?)
- scientific article; zbMATH DE number 3320125 (Why is no real title available?)
- Instance optimal learning of discrete distributions
- Learning from untrusted data
- Learning halfspaces with malicious noise
- Low rank approximation with entrywise \(\ell_1\)-norm error
- Most tensor problems are NP-hard
- Optimal algorithms for testing closeness of discrete distributions
- Robust Statistics
- Semidefinite programming based preconditioning for more robust near-separable nonnegative matrix factorization
- Testing closeness of discrete distributions
- Testing properties of collections of distributions
- The performance of universal encoding
- Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics
Cited in
(5)- Confidence regions and minimax rates in outlier-robust estimation on the probability simplex
- Robust estimators in high-dimensions without the computational intractability
- Learning from untrusted data
- Efficiently learning structured distributions from untrusted batches
- Learning from similar linear representations: adaptivity, minimaxity, and robustness
This page was built for publication: Learning discrete distributions from untrusted batches
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4993316)
