The K-armed dueling bandits problem, where the feedback is in the form of noisy pairwise preferences, has been widely studied due its applications in information retrieval, recommendation systems, etc. Motivated by co...
详细信息
ISBN:
(纸本)9781713899921
The K-armed dueling bandits problem, where the feedback is in the form of noisy pairwise preferences, has been widely studied due its applications in information retrieval, recommendation systems, etc. Motivated by concerns that user preferences/tastes can evolve over time, we consider the problem of dueling bandits with distribution shifts. Specifically, we study the recent notion of significant shifts [Suk and Kpotufe, 2022], and ask whether one can design an adaptive algorithm for the dueling problem with O(root K (L) over tildeT) dynamic regret, where (L) over tilde is the (unknown) number of significant shifts in preferences. We show that the answer to this question depends on the properties of underlying preference distributions. Firstly, we give an impossibility result that rules out any algorithm with O(root K (L) over tildeT) dynamic regret under the well-studied Condorcet and SST classes of preference distributions. Secondly, we show that SSTnSTI is the largest amongst popular classes of preference distributions where it is possible to design such an algorithm. Overall, our results provides an almost complete resolution of the above question for the hierarchy of distribution classes.
This paper introduces an adaptive method that significantly improves visualization quality of reconstructed strains in phase-sensitive optical coherence elastography (OCE). The strain is estimated by finding axial gra...
详细信息
ISBN:
(纸本)9781510667891;9781510667907
This paper introduces an adaptive method that significantly improves visualization quality of reconstructed strains in phase-sensitive optical coherence elastography (OCE). The strain is estimated by finding axial gradients of interframe phase variations and the phase-variation gradients are estimated over a certain scale. The noise level of the so-found strain maps heavily depends on the chosen scale that is used for gradient estimation. Choosing a scale that is too small or too large can degrade the results of elastographic visualization. In real conditions the spatial strain distribution usually is essentially inhomogeneous. Obtaining the best results in different areas of OCT scans requires utilization of different scales, although usually some fixed "compromise" scale over the entire OCT image is used to estimate phase-variation gradients. To improve the quality of strain maps in phase-sensitive OCE, we propose a method of automatic adaptive selection of this scale depending on the level of local strain in the visualized area. The proposed method is elucidated using on both numerically simulated and real OCT scans which are characterized by significant spatial inhomogeneity of strains.
Block-term decomposition (BTD), which factorizes a tensor (aka a multiway array) into block components of low rank, has been a powerful processing tool for multivariate and high-dimensional data analysis. In this pape...
详细信息
ISBN:
(纸本)9781665452458
Block-term decomposition (BTD), which factorizes a tensor (aka a multiway array) into block components of low rank, has been a powerful processing tool for multivariate and high-dimensional data analysis. In this paper, we propose a novel tensor tracking method called SBTD for factorizing tensors derived from multidimensional data streams under the BTD format. Thanks to the alternating optimization framework, SBTD first applies a regularized least-squares solver to estimate the temporal factor of the underlying streaming tensor. Then, SBTD adopts an adaptive filter to track the non-temporal tensor factors over time by minimizing a weighted least-squares cost function. Numerical experiments indicate that SBTD is capable of tensor tracking with competitive performance compared to the state-of-the-art BTD algorithms.
We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements. Given an n x n matrix A, a general linear measurement S(A), for an n x n matrix S, is just the inner pro...
详细信息
ISBN:
(纸本)9781713899921
We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements. Given an n x n matrix A, a general linear measurement S(A), for an n x n matrix S, is just the inner product of S and A, each treated as n(2)-dimensional vectors. By performing as few linear measurements as possible on a rank-r matrix A, we hope to construct a matrix (A) over cap that satisfies parallel to A - (A) over cap parallel to(2)(F) <= c parallel to A parallel to(2)(F), (1) for a small constant c. Here parallel to A parallel to(F) denotes the Frobenius norm (Sigma(i,j) A(i,j)(2))(1/2). It is commonly assumed that when measuring A with S, the response is corrupted with an independent Gaussian random variable of mean 0 and variance sigma(2). Candes and Plan (IEEE Trans. Inform. Theory 2011) study non-adaptive algorithms for low rank matrix recovery using random linear measurements. They use the restricted isometry property (RIP) of Random Gaussian Matrices to give tractable algorithms to estimate A from the measurements. At the edge of the noise level where recovery is information-theoretically feasible, it is known that their non-adaptive algorithms need to perform Omega(n(2)) measurements, which amounts to reading the entire matrix. An important question is whether adaptivity helps in decreasing the overall number of measurements. While for the related problem of sparse recovery, adaptive algorithms have been extensively studied, as far as we are aware adaptive algorithms and lower bounds on them seem largely unexplored for matrix recovery. We show that any adaptive algorithm that uses k linear measurements in each round and outputs an approximation as in (1) with probability >= 9/10 must run for t = Omega(log(n(2)/k)/ log log n) rounds. Our lower bound shows that any adaptive algorithm which uses n(2-beta) (for any constant beta > 0) linear measurements in each round must run for Omega(log n/ log log n) rounds to compute a good reconstruction wit
Abstract: Small-dimension unmanned aerial vehicles (SUAV) as objects of radar surveillance feature extremely small values of the effective radar cross section and the capability to carry out intense maneuvers and to h...
详细信息
We present an asymptotic analysis of adaptive methods for L-p approximation of functions f is an element of C-r([a, b]), where 1 <= p <= +infinity. The methods rely on piecewise polynomial interpolation of degre...
详细信息
We present an asymptotic analysis of adaptive methods for L-p approximation of functions f is an element of C-r([a, b]), where 1 <= p <= +infinity. The methods rely on piecewise polynomial interpolation of degree r - 1 with adaptive strategy of selecting m subintervals. The optimal speed of convergence is in this case of order m(-r) and it is already achieved by the uniform (nonadaptive) subdivision of the initial interval;however, the asymptotic constant crucially depends on the chosen strategy. We derive asymptotically best adaptive strategies and show their applicability to automatic L-p approximation with a given accuracy epsilon.
With the development and evolution of information technology, cloud-based online programming environments are increasingly preferred by developers, but the current cloud editor platform services generally suffer from ...
详细信息
Computing the optimal solution to a spatial filtering problems in a Wireless Sensor Network can incur large bandwidth and computational requirements if an approach relying on data centralization is used. The so-called...
详细信息
This paper investigates cross-polarization interference cancellation (XPIC) techniques in satellite communication systems. The LMS, DD-LMS, and CMA algorithms are studied for mitigating polarization interference. Simu...
详细信息
To solve the problem that the traditional BP(Backpropagation) neural optimization UWB(Ultra-Wideband) localization algorithm is prone to fall into the problem of poor localization effect caused by local optimization, ...
详细信息
暂无评论