Stochastic Low-Rank Tensor Bandits for Multi-Dimensional Online Decision Making
From MaRDI portal
Cites work
- 10.1162/153244303321897663
- A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion
- A Tutorial on Thompson Sampling
- An information-theoretic analysis of Thompson sampling
- An optimal statistical and computational framework for generalized tensor estimation
- Asymptotically efficient adaptive allocation rules
- Bandit algorithms
- Cross: efficient low-rank tensor completion
- Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
- Finite-time analysis of the multiarmed bandit problem
- Introduction to nonparametric estimation
- Multilayer tensor factorization with applications to recommender systems
- Nonconvex Low-Rank Tensor Completion from Noisy Data
- Nuclear norm of higher-order tensors
- On tensor completion via nuclear norm minimization
- Provable sparse tensor decomposition
- Regret analysis of stochastic and nonstochastic multi-armed bandit problems
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Statistically optimal and computationally efficient low rank tensor completion from noisy entries
- Tensor Decompositions and Applications
- Tensor SVD: Statistical and Computational Limits
Cited in
(2)
This page was built for publication: Stochastic Low-Rank Tensor Bandits for Multi-Dimensional Online Decision Making
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6995029)
