Learning-to-learn or meta-learning focuses on developing algorithms that leverage prior experience to quickly acquire new skills or adapt to novel environments. A crucial component of meta-learning is representation learning, which aims to construct data representations capable of transferring knowledge across multiple tasks—a critical advantage in data-scarce settings. We study how representation learning can improve the efficiency of bandit problems. We consider $T$ $d$-dimensional linear bandits that share a common low-dimensional linear representation. We provide provably fast, sample-efficient algorithms to address the two key problems in meta-learning: (1) learning a common set of features from multiple related bandit tasks and (2) transferring this knowledge to new, unseen bandit tasks. We validated the theoretical results through numerical experiments using real-world and synthetic datasets, comparing them against benchmark algorithms.

In recent work [1], we developed a distributed stochastic multi-arm contextual bandit algorithm to learn optimal actions when the contexts are unknown, and M agents work collaboratively under the coordination of a central server to minimize the total regret. In our model, the agents observe only the context distribution and the exact context is unknown to the agents. Such a situation arises, for instance, when the context itself is a noisy measurement or based on a prediction mechanism. By performing a feature vector transformation and by leveraging the UCB algorithm, we proposed a UCB algorithm for stochastic bandits with context distribution. In this paper, we test our algorithm on a real-world dataset and investigate the interactions between drugs and proteins. For this we perform a data pre-processing step to fit the model and we evaluated the performance of our algorithm for the drug-protein interaction study as compared to other benchmark algorithm. Furthermore, we present the results of biological experiments and draw inferences from our findings.

This work studies our recently developed algorithm, decentralized alternating projected gradient descent algorithm (Dec-AltGDmin), for recovering a low rank (LR) matrix from independent column-wise linear projections in a decentralized setting. This means that the observed data is spread across L agents and there is no central coordinating node. Since this problem is non-convex and since it involves a subspace recovery step, most existing literature from decentralized optimization is not useful. We demonstrate using extensive numerical simulations and communication, time, and sample complexity comparisons that (i) existing decentralized gradient descent (GD) approaches fail, and (ii) other common solution approaches on LR recovery literature – projected GD, alternating GD and alternating minimization (AltMin) – either have a higher communication (and time) complexity or a higher sample complexity. Communication complexity is often the most important concern in decentralized learning.

We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T linear contextual bandits with dimension simultaneously, and these T bandit tasks collectively share a common linear representation with a dimensionality of r ≪ d. We present a new algorithm based on alternating projected gradient descent (GD) and minimization estimator to recover a low-rank feature matrix. We obtain constructive provable guarantees for our estimator that provide a lower bound on the required sample complexity and an upper bound on the iteration complexity (total number of iterations needed to achieve a certain error level). Using the proposed estimator, we present a multi-task learning algorithm for linear contextual bandits and prove the regret bound of our algorithm. We presented experiments and compared the performance of our algorithm against benchmark algorithms.

We study the federated stochastic multi-arm contex-tual bandits with unknown contexts, in which$M$agents face$M$different bandit problems and collaborate to learn. The communication model consists of a central server and$M$agents, and the agents share their estimates with the central server periodically to learn to choose optimal actions to minimize the total regret. We assume that the exact contexts are not observable, and the agents observe only a distribution of contexts. Such a situation arises, for instance, when the context itself is a noisy measurement or based on a prediction mechanism. Our goal is to develop a distributed and federated algorithm that facilitates collaborative learning among the agents to select a sequence of optimal actions to maximize the cumulative reward. By performing a feature vector transformation, we propose an elimination-based algorithm and prove the regret bound for linearly parametrized reward functions. Finally, we validated the performance of our algorithm and compared it with another baseline approach using numerical simulations on synthetic data and the real-world movielens dataset.

This work studies our recently developed decentralized algorithm, decentralized alternating projected gradient descent algorithm, called Dec-AltProjGDmin, for solving the following low-rank (LR) matrix recovery problem: recover an LR matrix from independent column-wise linear projections (LR column-wise Compressive Sensing). In recent work, we presented constructive convergence guarantees for Dec-AltProjGDmin under simple assumptions. By "constructive", we mean that the convergence time lower bound is provided for achieving any error level ε. However, our guarantee was stated for the equal neighbor consensus algorithm (at each iteration, each node computes the average of the data of all its neighbors) while most existing results do not assume the use of a specific consensus algorithm, but instead state guarantees in terms of the weights matrix eigenvalues. In order to compare with these results, we first modify our result to be in this form. Our second and main contribution is a theoretical and experimental comparison of our new result with the best existing one from the decentralized GD literature that also provides a convergence time bound for values of ε that are large enough. The existing guarantee is for a different problem setting and holds under different assumptions than ours and hence the comparison is not very clear cut. However, we are not aware of any other provably correct algorithms for decentralized LR matrix recovery in any other settings either.