Results 11 to 20 of about 358,125 (307)
Asymptotic optimality in stochastic optimization [PDF]
The Annals of Statistics, 2021 We study local complexity measures for stochastic convex optimization problems, providing a local minimax theory analogous to that of Hájek and Le Cam for classical statistical problems. We give complementary optimality results, developing fully online methods that adaptively achieve optimal convergence guarantees. Our results provide function-specific
Duchi, John C., Ruan, Feng
openaire +3 more sources
Asymptotic Optimality for Decentralised Bandits [PDF]
Dynamic Games and Applications, 2022 AbstractWe consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm which builds upon and improves the Gossip-Insert-Eliminate method of Chawla et al. (International conference
Conor Newton +2 more
openaire +10 more sources
Revisiting the Asymptotic Optimality of RRT [PDF]
2020 IEEE International Conference on Robotics and Automation (ICRA), 2020 RRT* is one of the most widely used sampling-based algorithms for asymptotically-optimal motion planning. This algorithm laid the foundations for optimality in motion planning as a whole, and inspired the development of numerous new algorithms in the field, many of which build upon RRT* itself.
Kiril Solovey +4 more
openaire +3 more sources
Asymptotic optimality of antidictionary codes [PDF]
2010 IEEE International Symposium on Information Theory, 2010 5 pages, to appear in the proceedings of 2010 IEEE International Symposium on Information Theory (ISIT2010)
Takahiro Ota, Hiroyoshi Morita
openaire +2 more sources
Asymptotically Optimal Agents [PDF]
, 2011 21 LaTeX ...
Tor Lattimore, Marcus Hutter
openaire +4 more sources
On Thompson Sampling and Asymptotic Optimality [PDF]
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017 We discuss some recent results on Thompson sampling for nonparametric reinforcement learning in countable classes of general stochastic environments. These environments can be non-Markovian, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its value converges in ...
Jan Leike +3 more
openaire +2 more sources
Asymptotic optimality of twist-untwist protocols for Heisenberg scaling in atom-based sensing
Physical Review Research, 2022 Twist-untwist protocols for quantum metrology consist of a serial application of (1) unitary nonlinear dynamics (e.g., spin squeezing or Kerr nonlinearity), (2) parameterized dynamics U(ϕ) (e.g., a collective rotation or phase space displacement), and (3)
T. J. Volkoff, Michael J. Martin
doaj +1 more source
Two New Classes of Codebooks Asymptotically Achieving the Welch Bound
IEEE Access, 2021 Exponential sums over Galois rings have many applications in coding theory, cryptography and algebraic combinatorics. In this article, we employ additive characters and multiplicative characters over Galois rings to present two classes of codebooks, and ...
Shimin Sun, Li Han, Yang Yan, Yao Yao
doaj +1 more source
Asymptotic optimality of sequential designs for estimation
International Journal of Mathematics and Mathematical Sciences, 1995 This paper is concerned with the problem of allocating a fixed number of trials between K independent populations from the exponential family, in order to estimate a linear combination of the means with squared error loss.
Kamel Rekab
doaj +1 more source
Asymptotically Optimal Covering Designs
Journal of Combinatorial Theory, Series A, 1996 A (v,k,t) covering design, or covering, is a family of k-subsets, called blocks, chosen from a v-set, such that each t-subset is contained in at least one of the blocks. The number of blocks is the covering's size}, and the minimum size of such a covering is denoted by C(v,k,t).
Gordon, Daniel +3 more
openaire +4 more sources