arXiv subjects

Guojun Xiong

Publications and source records attributed to Guojun Xiong.

44 records · Page 3Linked to original sources

arXiv2023

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with $\mathcal{O}(1/k^{2/3})$ convergence rate, where $k$ is the number of iterations.

cs.LG↗

arXiv2023

Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation

We consider the problem of content caching at the wireless edge to serve a set of end users via unreliable wireless channels so as to minimize the average latency experienced by end users due to the constrained wireless edge cache capacity. We formulate this problem as a Markov decision process, or more specifically a restless multi-armed bandit problem, which is provably hard to solve. We begin by investigating a discounted counterpart, and prove that it admits an optimal policy of the threshold-type. We then show that this result also holds for average latency problem. Using this structural result, we establish the indexability of our problem, and employ the Whittle index policy to minimize average latency. Since system parameters such as content request rates and wireless channel conditions are often unknown and time-varying, we further develop a model-free reinforcement learning algorithm dubbed as Q^{+}-Whittle that relies on Whittle index policy. However, Q^{+}-Whittle requires to store the Q-function values for all state-action pairs, the number of which can be extremely large for wireless edge caching. To this end, we approximate the Q-function by a parameterized function class with a much smaller dimension, and further design a Q^{+}-Whittle algorithm with linear function approximation, which is called Q^{+}-Whittle-LFA. We provide a finite-time bound on the mean-square error of Q^{+}-Whittle-LFA. Simulation results using real traces demonstrate that Q^{+}-Whittle-LFA yields excellent empirical performance.

cs.NI↗

arXiv2022

Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players have \textit{full access} to all arms and receive no reward when pulling the same arm. Hence all players solve the same bandit problem with the goal of maximizing their cumulative reward. However, these settings neglect several important factors in many real-world applications, where players have \textit{limited access} to \textit{a dynamic local subset of arms} (i.e., an arm could sometimes be ``walking'' and not accessible to the player). To this end, this paper proposes a \textit{multi-player multi-armed walking bandits} model, aiming to address aforementioned modeling issues. The goal now is to maximize the reward, however, players can only pull arms from the local subset and only collect a full reward if no other players pull the same arm. We adopt Upper Confidence Bound (UCB) to deal with the exploration-exploitation tradeoff and employ distributed optimization techniques to properly handle collisions. By carefully integrating these two techniques, we propose a decentralized algorithm with near-optimal guarantee on the regret, and can be easily implemented to obtain competitive empirical performance.

cs.LG↗

arXiv2022

Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms so as to maximize the expected value of the cumulative rewards collected. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy. Our policy is well-defined even if the underlying MDPs are not indexable. We prove that it is asymptotically optimal when the activation budget and number of arms are scaled up, while keeping their ratio as a constant. For the case when the system parameters are unknown, we develop a learning algorithm. Our learning algorithm uses the principle of optimism in the face of uncertainty and further uses a generative model in order to fully exploit the structure of Occupancy-Measured-Reward Index Policy. We call it the R(MA)^2B-UCB algorithm. As compared with the existing algorithms, R(MA)^2B-UCB performs close to an offline optimum policy, and also achieves a sub-linear regret with a low computational complexity. Experimental results show that R(MA)^2B-UCB outperforms the existing algorithms in both regret and run time.

cs.LG↗

arXiv2021

Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers

With the increasing demand for large-scale training of machine learning models, consensus-based distributed optimization methods have recently been advocated as alternatives to the popular parameter server framework. In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset. However, the synchronization phase can be time consuming due to the need to wait for \textit{stragglers}, i.e., slower workers. An efficient way to mitigate this effect is to let each worker wait only for updates from the fastest neighbors before updating its local parameter. The remaining neighbors are called \textit{backup workers.} To minimize the globally training time over the network, we propose a fully distributed algorithm to dynamically determine the number of backup workers for each worker. We show that our algorithm achieves a linear speedup for convergence (i.e., convergence performance increases linearly with respect to the number of workers). We conduct extensive experiments on MNIST and CIFAR-10 to verify our theoretical results.

cs.LG↗

arXiv2021

Learning Augmented Index Policy for Optimal Service Placement at the Network Edge

We consider the problem of service placement at the network edge, in which a decision maker has to choose between $N$ services to host at the edge to satisfy the demands of customers. Our goal is to design adaptive algorithms to minimize the average service delivery latency for customers. We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service. However, solving this $N$-services MDP is computationally expensive due to the curse of dimensionality. To overcome this challenge, we show that the optimal policy for a single-service MDP has an appealing threshold structure, and derive explicitly the Whittle indices for each service as a function of the number of requests from customers based on the theory of Whittle index policy. Since request arrival and service delivery rates are usually unknown and possibly time-varying, we then develop efficient learning augmented algorithms that fully utilize the structure of optimal policies with a low learning regret. The first of these is UCB-Whittle, and relies upon the principle of optimism in the face of uncertainty. The second algorithm, Q-learning-Whittle, utilizes Q-learning iterations for each service by using a two time scale stochastic approximation. We characterize the non-asymptotic performance of UCB-Whittle by analyzing its learning regret, and also analyze the convergence properties of Q-learning-Whittle. Simulation results show that the proposed policies yield excellent empirical performance.

cs.NI↗

arXiv2020

Leveraging Subspace Information for Low-Rank Matrix Reconstruction

The problem of low-rank matrix reconstruction arises in various applications in communications and signal processing. The state of the art research largely focuses on the recovery techniques that utilize affine maps satisfying the restricted isometry property (RIP). However, the affine map design and reconstruction under a priori information, i.e., column or row subspace information, has not been thoroughly investigated. To this end, we present designs of affine maps and reconstruction algorithms that fully exploit the low-rank matrix subspace information. Compared to the randomly generated affine map, the proposed affine map design permits an enhanced reconstruction. In addition, we derive an optimal representation of low-rank matrices, which is exploited to optimize the rank and subspace of the estimate by adapting them to the noise level in order to achieve the minimum mean square error (MSE). Moreover, in the case when the subspace information is not a priori available, we propose a two-step algorithm, where, in the first step, it estimates the column subspace of a low-rank matrix, and in the second step, it exploits the estimated information to complete the reconstruction. The simulation results show that the proposed algorithm achieves robust performance with much lower complexity than existing reconstruction algorithms.

eess.SP↗

arXiv2019

Decorrelation Deep Learning for Fingerprint-based Indoor Localization

Indoor localization is of particular interest due to its immense practical applications. However, the rich multipath and high penetration loss of indoor wireless signal propagation make this task arduous. Though recently studied fingerprint-based techniques can handle the multipath effects, the sensitivity of the localization performance to channel fluctuation is a drawback. To address the latter challenge, we adopt an artificial multi-layer neural network (MNN) to learn the complex channel impulse responses (CIRs) as fingerprint measurements. However, the performance of the location classification using MNN critically depends on the correlation among the training data. Therefore, we design two different decorrelation filters that preprocess the training data for discriminative learning. The first one is a linear whitening filter combined with the principal component analysis (PCA), which forces the covariance matrix of different feature dimensions to be identity. The other filter is a nonlinear quantizer that is optimized to minimize the distortion incurred by the quantization. Numerical results using indoor channel models illustrate the significant improvement of the proposed decorrelation MNN (DMNN) compared to other benchmarks.

eess.SP↗