Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Adaptive Estimation of Random Vectors with Bandit Feedback: A mean-squared error viewpoint (2203.16810v3)

Published 31 Mar 2022 in cs.LG

Abstract: We consider the problem of sequentially learning to estimate, in the mean squared error (MSE) sense, a Gaussian $K$-vector of unknown covariance by observing only $m < K$ of its entries in each round. We first establish a concentration bound for MSE estimation. We then frame the estimation problem with bandit feedback, and propose a variant of the successive elimination algorithm. We also derive a minimax lower bound to understand the fundamental limit on the sample complexity of this problem.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. Correlated bandits or: How to minimize mean-squared error online, in: International Conference on Machine Learning, PMLR. pp. 686–694.
  2. Optimal rates of convergence for covariance matrix estimation. The Annals of Statistics 38, 2118–2144.
  3. Trading off rewards and errors in multi-armed bandits, in: International Conference on Artificial Intelligence and Statistics, PMLR. pp. 709–717.
  4. Pac bounds for multi-armed bandit and markov decision processes, in: International Conference on Computational Learning Theory, Springer. pp. 255–270.
  5. Near-optimal sensor placements in gaussian processes, in: International conference on Machine learning, pp. 265–272.
  6. Correlated multi-armed bandits with a latent random source, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE. pp. 3572–3576.
  7. Notes for ECE 534: an exploration of random processes for engineers. Univ. of Illinois at Urbana–Champaign .
  8. On the complexity of best arm identification in multi-armed bandit models. The Journal of Machine Learning Research .
  9. Efficient Sensor Placement Optimization for Securing Large Water Distribution Networks. Journal of Water Resources Planning and Management 134, 516–526.
  10. Bandit algorithms. Cambridge University Press.
  11. Most correlated arms identification, in: Confernce on Learning Theory, pp. 623–637.
  12. Learning probabilistic models of cellular network traffic with applications to resource management, in: IEEE International Symposium on Dynamic Spectrum Access Networks, pp. 82–91.
  13. High dimensional statistics. Lecture notes for course 18S997 .
  14. Adaptive estimation of random vectors with bandit feedback, in: Indian Control Conference, pp. 1–2.
  15. High-dimensional statistics: A non-asymptotic viewpoint. Cambridge University Press.

Summary

We haven't generated a summary for this paper yet.