اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
132
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given $n$ arms with unknown reward distributions, as well as a family $mathcal{F}$ of feasible subsets over the arms. Our goal is to identify the feasible subset in $mathcal{F}$ with the maximum total mean using as few samples as possible. The problem generalizes the classical best arm identification problem and the top-$k$ arm identification problem, both of which have attracted significant attention in recent years. We provide a novel instance-wise lower bound for the sample complexity of the problem, as well as a nontrivial sampling algorithm, matching the lower bound up to a factor of $ln|mathcal{F}|$. For an important class of combinatorial families, we also provide polynomial time implementation of the sampling algorithm, using the equivalence of separation and optimization for convex program, and approximate Pareto curves in multi-objective optimization. We also show that the $ln|mathcal{F}|$ factor is inevitable in general through a nontrivial lower bound construction. Our results significantly improve several previous results for several important combinatorial constraints, and provide a tighter understanding of the general Best-Set problem. We further introduce an even more general problem, formulated in geometric terms. We are given $n$ Gaussian arms with unknown means and unit variance. Consider the $n$-dimensional Euclidean space $mathbb{R}^n$, and a collection $mathcal{O}$ of disjoint subsets. Our goal is to determine the subset in $mathcal{O}$ that contains the $n$-dimensional vector of the means. The problem generalizes most pure exploration bandit problems studied in the literature. We provide the first nearly optimal sample complexity upper and lower bounds for the problem.
قيم البحث
اقرأ أيضاً
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better empirical pe
rformance compared to the state of the art methods. In this paper, we provide a novel regret analysis for Thompson Sampling that simultaneously proves both the optimal problem-dependent bound of $(1+epsilon)sum_i frac{ln T}{Delta_i}+O(frac{N}{epsilon^2})$ and the first near-optimal problem-independent bound of $O(sqrt{NTln T})$ on the expected regret of this algorithm. Our near-optimal problem-independent bound solves a COLT 2012 open problem of Chapelle and Li. The optimal problem-dependent regret bound for this problem was first proven recently by Kaufmann et al. [ALT 2012]. Our novel martingale-based analysis techniques are conceptually simple, easily extend to distributions other than the Beta distribution, and also extend to the more general contextual bandits setting [Manuscript, Agrawal and Goyal, 2012].
In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the $k$ arms with the largest means by taking as few samples as possible. In this paper, we make pr
ogress towards a complete characterization of the instance-wise sample complexity bounds for the Best-$k$-Arm problem. On the lower bound side, we obtain a novel complexity term to measure the sample complexity that every Best-$k$-Arm instance requires. This is derived by an interesting and nontrivial reduction from the Best-$1$-Arm problem. We also provide an elimination-based algorithm that matches the instance-wise lower bound within doubly-logarithmic factors. The sample complexity of our algorithm strictly dominates the state-of-the-art for Best-$k$-Arm (module constant factors).
Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user. However, the stationary CB model may be too
simple to apply to real-world problems, where user preferences may change over time. Considering piecewise-stationary environments, two efficient algorithms, texttt{GLRT-CascadeUCB} and texttt{GLRT-CascadeKL-UCB}, are developed and shown to ensure regret upper bounds on the order of $mathcal{O}(sqrt{NLTlog{T}})$, where $N$ is the number of piecewise-stationary segments, and $T$ is the number of time slots. At the crux of the proposed algorithms is an almost parameter-free change-point detector, the generalized likelihood ratio test (GLRT). Comparing with existing works, the GLRT-based algorithms: i) are free of change-point-dependent information for choosing parameters; ii) have fewer tuning parameters; iii) improve at least the $L$ dependence in regret upper bounds. In addition, we show that the proposed algorithms are optimal (up to a logarithm factor) in terms of regret by deriving a minimax lower bound on the order of $Omega(sqrt{NLT})$ for piecewise-stationary CB. The efficiency of the proposed algorithms relative to state-of-the-art approaches is validated through numerical experiments on both synthetic and real-world datasets.
Given a mixture between two populations of coins, positive coins that each have -- unknown and potentially different -- bias $geqfrac{1}{2}+Delta$ and negative coins with bias $leqfrac{1}{2}-Delta$, we consider the task of estimating the fraction $rh
o$ of positive coins to within additive error $epsilon$. We achieve an upper and lower bound of $Theta(frac{rho}{epsilon^2Delta^2}logfrac{1}{delta})$ samples for a $1-delta$ probability of success, where crucially, our lower bound applies to all fully-adaptive algorithms. Thus, our sample complexity bounds have tight dependence for every relevant problem parameter. A crucial component of our lower bound proof is a decomposition lemma (see Lemmas 17 and 18) showing how to assemble partially-adaptive bounds into a fully-adaptive bound, which may be of independent interest: though we invoke it for the special case of Bernoulli random variables (coins), it applies to general distributions. We present simulation results to demonstrate the practical efficacy of our approach for realistic problem parameters for crowdsourcing applications, focusing on the rare events regime where $rho$ is small. The fine-grained adaptive flavor of both our algorithm and lower bound contrasts with much previous work in distributional testing and learning.
We study online pricing algorithms for the Bayesian selection problem with production constraints and its generalization to the laminar matroid Bayesian online selection problem. Consider a firm producing (or receiving) multiple copies of different p
roduct types over time. The firm can offer the products to arriving buyers, where each buyer is interested in one product type and has a private valuation drawn independently from a possibly different but known distribution. Our goal is to find an adaptive pricing for serving the buyers that maximizes the expected social-welfare (or revenue) subject to two constraints. First, at any time the total number of sold items of each type is no more than the number of produced items. Second, the total number of sold items does not exceed the total shipping capacity. This problem is a special case of the well-known matroid Bayesian online selection problem studied in [Kleinberg and Weinberg, 2012], when the underlying matroid is laminar. We give the first Polynomial-Time Approximation Scheme (PTAS) for the above problem as well as its generalization to the laminar matroid Bayesian online selection problem when the depth of the laminar family is bounded by a constant. Our approach is based on rounding the solution of a hierarchy of linear programming relaxations that systematically strengthen the commonly used ex-ante linear programming formulation of these problems and approximate the optimum online solution with any degree of accuracy. Our rounding algorithm respects the relaxed constraints of higher-levels of the laminar tree only in expectation, and exploits the negative dependency of the selection rule of lower-levels to achieve the required concentration that guarantees the feasibility with high probability.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
