Dynamic Spectrum Access using Stochastic Multi-User Bandits

A stochastic multi-user multi-armed bandit framework is used to develop algorithms for uncoordinated spectrum access. In contrast to prior work, it is assumed that rewards can be non-zero even under collisions, thus allowing for the number of users to be greater than the number of channels. The proposed algorithm consists of an estimation phase and an allocation phase. It is shown that if every user adopts the algorithm, the system wide regret is order-optimal of order $O(\log T)$ over a time-horizon of duration $T$. The regret guarantees hold for both the cases where the number of users is greater than or less than the number of channels. The algorithm is extended to the dynamic case where the number of users in the system evolves over time, and is shown to lead to sub-linear regret.

Robust Mean Estimation in High Dimensions via $\ell_0$ Minimization

We study the robust mean estimation problem in high dimensions, where $\alpha <0.5$ fraction of the data points can be arbitrarily corrupted. Motivated by compressive sensing, we formulate the robust mean estimation problem as the minimization of the $\ell_0$-`norm' of the outlier indicator vector, under second moment constraints on the inlier data points. We prove that the global minimum of this objective is order optimal for the robust mean estimation problem, and we propose a general framework for minimizing the objective. We further leverage the $\ell_1$ and $\ell_p$ $(0<p<1)$, minimization techniques in compressive sensing to provide computationally tractable solutions to the $\ell_0$ minimization problem. Both synthetic and real data experiments demonstrate that the proposed algorithms significantly outperform state-of-the-art robust mean estimation methods.

Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access

Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems. In this paper we consider the scenario where users cannot communicate with each other. In addition, the environment may appear differently to different users, ${i.e.}$, the mean rewards as observed by different users for the same channel may be different. With this setup, we present a policy that achieves a regret of $O (\log{T})$. This paper has been accepted at Asilomar Conference on Signals, Systems, and Computers 2019.

Sequential Controlled Sensing for Composite Multihypothesis Testing

The problem of multi-hypothesis testing with controlled sensing of observations is considered. The distribution of observations collected under each control is assumed to follow a single-parameter exponential family distribution. The goal is to design a policy to find the true hypothesis with minimum expected delay while ensuring that the probability of error is below a given constraint. The decision-maker can control the delay by intelligently choosing the control for observation collection in each time slot. We derive a policy that satisfies the given constraint on the error probability. We also show that the policy is asymptotically optimal in the sense that it asymptotically achieves an information-theoretic lower bound on the expected delay.

Multi-player Multi-Armed Bandits with non-zero rewards on collisions for uncoordinated spectrum access

In this paper, we study the uncoordinated spectrum access problem using the multi-player multi-armed bandits framework. We consider a model where there is no central control and the users cannot communicate with each other. The environment may appear differently to different users, \textit{i.e.}, the mean rewards as seen by different users for a particular channel may be different. Additionally, in case of a collision, we allow for the colliding users to receive non-zero rewards. With this setup, we present a policy that achieves expected regret of order $O(\log^{2+\delta}{T})$ for some $\delta > 0$.

Information-Theoretic Understanding of Population Risk Improvement with Model Compression

We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression. We first prove that model compression reduces an information-theoretic bound on the generalization error; this allows for an interpretation of model compression as a regularization technique to avoid overfitting. We then characterize the increase in empirical risk with model compression using rate distortion theory. These results imply that the population risk could be improved by model compression if the decrease in generalization error exceeds the increase in empirical risk. We show through a linear regression example that such a decrease in population risk due to model compression is indeed possible. Our theoretical results further suggest that the Hessian-weighted $K$-means clustering compression approach can be improved by regularizing the distance between the clustering centers. We provide experiments with neural networks to support our theoretical assertions.

Tightening Mutual Information Based Bounds on Generalization Error

A mutual information based upper bound on the generalization error of a supervised learning algorithm is derived in this paper. The bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm, which requires weaker conditions on the loss function, but provides a tighter characterization of the generalization error than existing studies. Examples are further provided to demonstrate that the bound derived in this paper is tighter, and has a broader range of applicability. Application to noisy and iterative algorithms, e.g., stochastic gradient Langevin dynamics (SGLD), is also studied, where the constructed bound provides a tighter characterization of the generalization error than existing results.

Model change detection with application to machine learning

Model change detection is studied, in which there are two sets of samples that are independently and identically distributed (i.i.d.) according to a pre-change probabilistic model with parameter $\theta$, and a post-change model with parameter $\theta'$, respectively. The goal is to detect whether the change in the model is significant, i.e., whether the difference between the pre-change parameter and the post-change parameter $\|\theta-\theta'\|_2$ is larger than a pre-determined threshold $\rho$. The problem is considered in a Neyman-Pearson setting, where the goal is to maximize the probability of detection under a false alarm constraint. Since the generalized likelihood ratio test (GLRT) is difficult to compute in this problem, we construct an empirical difference test (EDT), which approximates the GLRT and has low computational complexity. Moreover, we provide an approximation method to set the threshold of the EDT to meet the false alarm constraint. Experiments with linear regression and logistic regression are conducted to validate the proposed algorithms.

Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access

A stochastic multi-user multi-armed bandit framework is used to develop algorithms for uncoordinated spectrum access. In contrast to prior work, the number of users is assumed to be unknown to each user and can possibly exceed the number of channels. Also, in contrast to prior work, it is assumed that rewards can be non-zero even under collisions. The proposed algorithm consists of an estimation phase and an allocation phase. It is shown that if every user adopts the algorithm, the system wide regret is constant with time with high probability. The regret guarantees hold for any number of users and channels, i.e., even when the number of users is less than the number of channels. The algorithm is extended to the dynamic case where the number of users in the system evolves over time and our algorithm leads to sub-linear regret.