arXiv subjects

Shana Moothedath

Publications and source records attributed to Shana Moothedath.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Task Representation Learning for Conservative Linear Bandits

This paper presents the Constrained Multi-Task Representation Learning (CMTRL) framework for linear bandits. We consider T linear bandit tasks in a d dimensional space, which share a common low-dimensional representation of dimension r, where r is much smaller than the minimum of d and T. Furthermore, tasks are constrained so that only actions meeting specific safety or performance requirements are allowed, referred to as conservative (safe) bandits. We introduce a novel algorithm, Safe-Alternating projected Gradient Descent and minimization (Safe-AltGDmin), to recover a low-rank feature matrix while satisfying the given constraints. Building on this algorithm, we propose a multi-task representation learning framework for conservative linear bandits and establish theoretical guarantees for its regret and sample complexity bounds. We presented experiments and compared the performance of our algorithm with benchmark algorithms.

cs.LG↗

arXiv2026

Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Markov Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d. The relatedness among the tasks is captured by a low-rank structure on the reward matrices. Learning shared representations across multiple RL tasks is challenging due to the complex and policy-dependent nature of data that leads to a temporal progression of error. Our approach adopts a reward-free reinforcement learning framework to first learn a data-collection policy. This policy then informs an exploration strategy for estimating the unknown reward matrices. Importantly, the data collected under this well-designed policy enable accurate estimation, which ultimately supports the learning of an near-optimal policy. Unlike existing approaches that rely on restrictive assumptions such as Gaussian features, incoherence conditions, or access to optimal solutions, we propose a low-rank matrix estimation method that operates under more general feature distributions encountered in RL settings. Theoretical analysis establishes that accurate low-rank matrix recovery is achievable under these relaxed assumptions, and we characterize the relationship between representation error and sample complexity. Leveraging the learned representation, we construct near-optimal policies and prove a regret bound. Experimental results demonstrate that our method effectively learns robust shared representations and task dynamics from finite data.

cs.LG↗

arXiv2026

Learning Shared Representations for Multi-Task Linear Bandits

Multi-task representation learning is an approach that learns shared latent representations across related tasks, facilitating knowledge transfer and improving sample efficiency. This paper introduces a novel approach to multi-task representation learning in linear bandits. We consider a setting with T concurrent linear bandit tasks, each with feature dimension d, that share a common latent representation of dimension r \ll min{d,T}$, capturing their underlying relatedness. We propose a new Optimism in the Face of Uncertainty Linear (OFUL) algorithm that leverages shared low-rank representations to enhance decision-making in a sample-efficient manner. Our algorithm first collects data through an exploration phase, estimates the shared model via spectral initialization, and then conducts OFUL based learning over a newly constructed confidence set. We provide theoretical guarantees for the confidence set and prove that the unknown reward vectors lie within the confidence set with high probability. We derive cumulative regret bounds and show that the proposed approach achieves \tilde{O}(\sqrt{drNT}), a significant improvement over solving the T tasks independently, resulting in a regret of \tilde{O}(dT\sqrt{N}). We performed numerical simulations to validate the performance of our algorithm for different problem sizes.

cs.LG↗

arXiv2026

Post-Decision State-Based Online Learning for Delay-Energy-Aware Flow Allocation in Wireless Systems

We develop a structure-aware reinforcement learning (RL) approach for delay- and energy-aware flow allocation in 5G User Plane Functions (UPFs). We consider a dynamic system with $K$ heterogeneous UPFs of varying capacities that handle stochastic arrivals of $M$ flow types, each with distinct rate requirements. We model the system as a Markov decision process (MDP) to capture the stochastic nature of flow arrivals and departures (possibly unknown), as well as the impact of flow allocation in the system. To solve this problem, we propose a post-decision state (PDS) based value iteration algorithm that exploits the underlying structure of the MDP. By separating action-controlled dynamics from exogenous factors, PDS enables faster convergence and efficient adaptive flow allocation, even in the absence of statistical knowledge about exogenous variables. Simulation results demonstrate that the proposed method converges faster and achieves lower long-term cost than standard Q-learning, highlighting the effectiveness of PDS-based RL for resource allocation in wireless networks.

eess.SP↗

arXiv2025

Diffusion-based Decentralized Federated Multi-Task Representation Learning

Representation learning is a widely adopted framework for learning in data-scarce environments to obtain a feature extractor or representation from various different yet related tasks. Despite extensive research on representation learning, decentralized approaches remain relatively underexplored. This work develops a decentralized projected gradient descent-based algorithm for multi-task representation learning. We focus on the problem of multi-task linear regression in which multiple linear regression models share a common, low-dimensional linear representation. We present an alternating projected gradient descent and minimization algorithm for recovering a low-rank feature matrix in a diffusion-based decentralized and federated fashion. We obtain constructive, provable guarantees that provide a lower bound on the required sample complexity and an upper bound on the iteration complexity of our proposed algorithm. We analyze the time and communication complexity of our algorithm and show that it is fast and communication-efficient. We performed numerical simulations to validate the performance of our algorithm and compared it with benchmark algorithms.

cs.LG↗

arXiv2025

Beyond Centralization: Provable Communication Efficient Decentralized Multi-Task Learning

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain largely underexplored. We study decentralized multi-task representation learning in which the features share a low-rank structure. We consider multiple tasks, each with a finite number of data samples, where the observations follow a linear model with task-specific parameters. In the decentralized setting, task data are distributed across multiple nodes, and information exchange between nodes is constrained by a communication network. The goal is to recover the underlying feature matrix whose rank is much smaller than both the parameter dimension and the number of tasks. We propose a new alternating projected gradient and minimization algorithm with provable accuracy guarantees. We provide comprehensive characterizations of the time, communication, and sample complexities. Importantly, the communication complexity is independent of the target accuracy, which significantly reduces communication cost compared to prior methods. Numerical simulations validate the theoretical analysis across different dimensions and network topologies, and demonstrate regimes in which decentralized learning outperforms centralized federated approaches.

cs.LG↗

arXiv2025

Byzantine Resilient Federated Multi-Task Representation Learning

In this paper, we propose BR-MTRL, a Byzantine-resilient multi-task representation learning framework that handles faulty or malicious agents. Our approach leverages representation learning through a shared neural network model, where all clients share fixed layers, except for a client-specific final layer. This structure captures shared features among clients while enabling individual adaptation, making it a promising approach for leveraging client data and computational power in heterogeneous federated settings to learn personalized models. To learn the model, we employ an alternating gradient descent strategy: each client optimizes its local model, updates its final layer, and sends estimates of the shared representation to a central server for aggregation. To defend against Byzantine agents, we employ two robust aggregation methods for client-server communication, Geometric Median and Krum. Our method enables personalized learning while maintaining resilience in distributed settings. We implemented the proposed algorithm in a federated testbed built using Amazon Web Services (AWS) platform and compared its performance with various benchmark algorithms and their variations. Through experiments using real-world datasets, including CIFAR-10 and FEMNIST, we demonstrated the effectiveness and robustness of our approach and its transferability to new unseen clients with limited data, even in the presence of Byzantine adversaries.

cs.LG↗

arXiv2025

Energy-Aware 6G Network Design: A Survey

6th Generation (6G) mobile networks are envisioned to support several new capabilities and data-centric applications for unprecedented number of users, potentially raising significant energy efficiency and sustainability concerns. This brings focus on sustainability as one of the key objectives in the their design. To move towards sustainable solution, research and standardization community is focusing on several key issues like energy information monitoring and exposure, use of renewable energy, and use of Artificial Intelligence/Machine Learning (AI/ML) for improving the energy efficiency in 6G networks. The goal is to build energy-aware solutions that takes into account the energy information resulting in energy efficient networks. Design of energy-aware 6G networks brings in new challenges like increased overheads in gathering and exposing of energy related information, and the associated user consent management. The aim of this paper is to provide a comprehensive survey of methods used for design of energy efficient 6G networks, like energy harvesting, energy models and parameters, classification of energy-aware services, and AI/ML-based solutions. The survey also includes few use cases that demonstrate the benefits of incorporating energy awareness into network decisions. Several ongoing standardization efforts in 3GPP, ITU, and IEEE are included to provide insights into the ongoing work and highlight the opportunities for new contributions. We conclude this survey with open research problems and challenges that can be explored to make energy-aware design feasible and ensure optimality regarding performance and energy goals for 6G networks.

cs.NI↗

arXiv2025

Decentralized Communication-Efficient Multi-Task Representation Learning

This work develops a provably accurate fully-decentralized alternating projected gradient descent (GD) algorithm for recovering a low rank (LR) matrix from mutually independent projections of each of its columns, in a fast and communication-efficient fashion. To our best knowledge, this work is the first attempt to develop a provably correct decentralized algorithm (i) for any problem involving the use of an alternating projected GD algorithm; (ii) and for any problem in which the constraint set to be projected to is a non-convex set.

cs.IT↗

arXiv2025

Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints

We present conservative distributed multi-task learning in stochastic linear contextual bandits with heterogeneous agents. This extends conservative linear bandits to a distributed setting where M agents tackle different but related tasks while adhering to stage-wise performance constraints. The exact context is unknown, and only a context distribution is available to the agents as in many practical applications that involve a prediction mechanism to infer context, such as stock market prediction and weather forecast. We propose a distributed upper confidence bound (UCB) algorithm, DiSC-UCB. Our algorithm constructs a pruned action set during each round to ensure the constraints are met. Additionally, it includes synchronized sharing of estimates among agents via a central server using well-structured synchronization steps. We prove the regret and communication bounds on the algorithm. We extend the problem to a setting where the agents are unaware of the baseline reward. For this setting, we provide a modified algorithm, DiSC-UCB2, and we show that the modified algorithm achieves the same regret and communication bounds. We empirically validated the performance of our algorithm on synthetic data and real-world Movielens-100K data.

cs.LG↗

arXiv2025

Neural Contextual Bandits Under Delayed Feedback Constraints

This paper presents a new algorithm for neural contextual bandits (CBs) that addresses the challenge of delayed reward feedback, where the reward for a chosen action is revealed after a random, unknown delay. This scenario is common in applications such as online recommendation systems and clinical trials, where reward feedback is delayed because the outcomes or results of a user's actions (such as recommendations or treatment responses) take time to manifest and be measured. The proposed algorithm, called Delayed NeuralUCB, uses an upper confidence bound (UCB)-based exploration strategy. Under the assumption of independent and identically distributed sub-exponential reward delays, we derive an upper bound on the cumulative regret over a T-length horizon. We further consider a variant of the algorithm, called Delayed NeuralTS, that uses Thompson Sampling-based exploration. Numerical experiments on real-world datasets, such as MNIST and Mushroom, along with comparisons to benchmark approaches, demonstrate that the proposed algorithms effectively manage varying delays and are well-suited for complex real-world scenarios.

cs.LG↗

arXiv2025

Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits

We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T contextual linear bandits with dimension d simultaneously, and these T bandit tasks collectively share a common linear representation with a dimensionality of r much smaller than d. We present a new algorithm based on alternating projected gradient descent (GD) and minimization estimator to recover a low-rank feature matrix. 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.

cs.LG↗

arXiv2024

Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis

We explore a stochastic contextual linear bandit problem where the agent observes a noisy, corrupted version of the true context through a noise channel with an unknown noise parameter. Our objective is to design an action policy that can approximate" that of an oracle, which has access to the reward model, the channel parameter, and the predictive distribution of the true context from the observed noisy context. In a Bayesian framework, we introduce a Thompson sampling algorithm for Gaussian bandits with Gaussian context noise. Adopting an information-theoretic analysis, we demonstrate the Bayesian regret of our algorithm concerning the oracle's action policy. We also extend this problem to a scenario where the agent observes the true context with some delay after receiving the reward and show that delayed true contexts lead to lower Bayesian regret. Finally, we empirically demonstrate the performance of the proposed algorithms against baselines.

cs.LG↗

arXiv2024

Federated Learning for Heterogeneous Bandits with Unobserved Contexts

We study the problem of federated stochastic multi-arm contextual bandits with unknown contexts, in which M agents are faced with different bandits and collaborate to learn. The communication model consists of a central server and the agents share their estimates with the central server periodically to learn to choose optimal actions in order to minimize the total regret. We assume that the exact contexts are not observable and the agents observe only a distribution of the 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 so as 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 on the real-world movielens dataset.

cs.LG↗

arXiv2024

Minimal Input Structural Modifications for Strongly Structural Controllability

This paper studies the problem of modifying the input matrix of a structured system to make the system strongly structurally controllable. We focus on the generalized structured systems that rely on zero/nonzero/arbitrary structure, i.e., some entries of system matrices are zeros, some are nonzero, and the remaining entries can be zero or nonzero (arbitrary). We analyze the feasibility of the problem, and if it is feasible, we reformulate it into another equivalent problem. This new formulation leads to a greedy heuristic algorithm. However, we also show that the greedy algorithm can give arbitrarily poor solutions for some special systems. Our alternative approach is a randomized Markov chain Monte Carlo-based algorithm. Unlike the greedy algorithm, this algorithm is guaranteed to converge to an optimal solution with high probability. Finally, we numerically evaluate the algorithms on random graphs to show that the algorithms perform well.

eess.SY↗

arXiv2022

Distributed Stochastic Bandit Learning with Delayed Context Observation

We consider the problem where M agents collaboratively interact with an instance of a stochastic K-armed contextual bandit, where K>>M. The goal of the agents is to simultaneously minimize the cumulative regret over all the agents over a time horizon T. We consider a setting where the exact context is observed after a delay and at the time of choosing the action the agents are unaware of the context and only a distribution on the set of contexts is available. Such a situation arises in different applications where at the time of the decision the context needs to be predicted (e.g., weather forecasting or stock market prediction), and the context can be estimated once the reward is obtained. We propose an Upper Confidence Bound (UCB)-based distributed algorithm and prove the regret and communications bounds for linearly parametrized reward functions. We validated the performance of our algorithm via numerical simulations on synthetic data and real-world Movielens data.

cs.LG↗

arXiv2022

Stochastic Conservative Contextual Linear Bandits

Many physical systems have underlying safety considerations that require that the strategy deployed ensures the satisfaction of a set of constraints. Further, often we have only partial information on the state of the system. We study the problem of safe real-time decision making under uncertainty. In this paper, we formulate a conservative stochastic contextual bandit formulation for real-time decision making when an adversary chooses a distribution on the set of possible contexts and the learner is subject to certain safety/performance constraints. The learner observes only the context distribution and the exact context is unknown, and the goal is to develop an algorithm that selects a sequence of optimal actions to maximize the cumulative reward without violating the safety constraints at any time step. By leveraging the UCB algorithm for this setting, we propose a conservative linear UCB algorithm for stochastic bandits with context distribution. We prove an upper bound on the regret of the algorithm and show that it can be decomposed into three terms: (i) an upper bound for the regret of the standard linear UCB algorithm, (ii) a constant term (independent of time horizon) that accounts for the loss of being conservative in order to satisfy the safety constraint, and (ii) a constant term (independent of time horizon) that accounts for the loss for the contexts being unknown and only the distribution being known. To validate the performance of our approach we perform extensive simulations on synthetic data and on real-world maize data collected through the Genomes to Fields (G2F) initiative.

cs.LG↗

arXiv2021

Fully Decentralized and Federated Low Rank Compressive Sensing

In this work we develop a fully decentralized, federated, and fast solution to the recently studied Low Rank Compressive Sensing (LRCS) problem: recover an nxq low-rank matrix from column-wise linear projections. An important application where this problem occurs, and a decentralized solution is desirable is in federated sketching: efficiently compressing the vast amounts of distributed images/videos generated by smartphones and various other devices while respecting the users' privacy. Images from different devices, once grouped by category, are similar and hence the matrix formed by the vectorized images of a certain category is well-modeled as being low rank. Suppose there are p nodes (say p smartphones), and each store a subset of the sketches of its images. We develop a decentralized projected gradient descent (GD) based approach to jointly reconstruct the images of all the phones/users from their respective stored sketches. The algorithm is such that the phones/users never share their raw data but only summaries of this data with the other phones at each algorithm iteration. Also, the reconstructed images of user g are obtained only locally. Other users cannot reconstruct them. Only the column span of the matrix is reconstructed globally. By "decentralized" we mean that there is no central node to which all nodes are connected and thus the only way to aggregate the summaries from the various nodes is by use of an iterative consensus algorithm that eventually provides an estimate of the aggregate at each node, as long as the network is strongly connected. We validated the effectiveness of our algorithm via extensive simulation experiments.

cs.DS↗