Search Results for author: Setareh Maghsudi

Found 25 papers, 5 papers with code

Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments

1 code implementation7 Sep 2023 Manuel Eberhardinger, Johannes Maucher, Setareh Maghsudi

Understanding the interactions of agents trained with deep reinforcement learning is crucial for deploying agents in games or the real world.

Atari Games Decision Making +3

Federated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization

no code implementations31 Aug 2023 Mariam Yahya, Setareh Maghsudi, Slawomir Stanczak

We then develop a model and solution based on the multi-objective multi-armed bandit theory to maximize the network coverage while minimizing the FL delay.

Federated Learning

Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards

no code implementations26 Jul 2023 Behzad Nourani-Koliji, Steven Bilaj, Amir Rezaei Balef, Setareh Maghsudi

In our nonstationary environment, variations in the base arms' distributions, causal relationships between rewards, or both, change the reward generation process.

Decision Making

Online Learning with Costly Features in Non-stationary Environments

1 code implementation18 Jul 2023 Saeed Ghoorchian, Evgenii Kortukov, Setareh Maghsudi

Maximizing long-term rewards is the primary goal in sequential decision-making problems.

Decision Making

Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewards

no code implementations18 Jul 2023 Saeed Ghoorchian, Setareh Maghsudi

We develop a policy that learns the structural dependencies from delayed feedback and utilizes that to optimize the decision-making while adapting to drifts.

Decision Making Decision Making Under Uncertainty

Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning

no code implementations29 Jun 2023 Qiang He, Tianyi Zhou, Meng Fang, Setareh Maghsudi

In ERC, we propose a regularizer that guides the approximation error tending towards the 1-eigensubspace, resulting in a more efficient and stable path of value approximation.

Reinforcement Learning (RL)

Cooperative Thresholded Lasso for Sparse Linear Bandit

no code implementations30 May 2023 Haniyeh Barghi, Xiaotong Cheng, Setareh Maghsudi

We present a novel approach to address the multi-agent sparse contextual linear bandit problem, in which the feature vectors have a high dimension $d$ whereas the reward function depends on only a limited set of features - precisely $s_0 \ll d$.

Dimensionality Reduction regression

Deep Learning and Image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks

no code implementations8 May 2023 Yuwen Cao, Tomoaki Ohtsuki, Setareh Maghsudi, Tony Q. S. Quek

In this paper, we develop a deep learning (DL)-guided hybrid beam and power allocation approach for multiuser millimeter-wave (mmWave) networks, which facilitates swift beamforming at the base station (BS).

Image Super-Resolution

Robustness Implies Fairness in Causal Algorithmic Recourse

2 code implementations7 Feb 2023 Ahmad-Reza Ehyaei, Amir-Hossein Karimi, Bernhard Schölkopf, Setareh Maghsudi

Algorithmic recourse aims to disclose the inner workings of the black-box decision process in situations where decisions have significant consequences, by providing recommendations to empower beneficiaries to achieve a more favorable outcome.

Adversarial Robustness Fairness

Linear Combinatorial Semi-Bandit with Causally Related Rewards

no code implementations25 Dec 2022 Behzad Nourani-Koliji, Saeed Ghoorchian, Setareh Maghsudi

The objective is to maximize the long-term average payoff, which is a linear function of the base arms' rewards and depends strongly on the network topology.

Decision Making

Hypothesis Transfer in Bandits by Weighted Models

no code implementations14 Nov 2022 Steven Bilaj, Sofien Dhouib, Setareh Maghsudi

We consider the problem of contextual multi-armed bandits in the setting of hypothesis transfer learning.

Multi-Armed Bandits Transfer Learning

A Learning-Based Approach to Approximate Coded Computation

no code implementations19 May 2022 Navneet Agrawal, Yuqin Qiu, Matthias Frey, Igor Bjelakovic, Setareh Maghsudi, Slawomir Stanczak, Jingge Zhu

Lagrange coded computation (LCC) is essential to solving problems about matrix polynomials in a coded distributed fashion; nevertheless, it can only solve the problems that are representable as matrix polynomials.

Distributed Task Management in Fog Computing: A Socially Concave Bandit Game

no code implementations28 Mar 2022 Xiaotong Cheng, Setareh Maghsudi

One strategy, namely bandit gradient ascent with momentum, is an online convex optimization algorithm with bandit feedback.

Decision Making Management

Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization

no code implementations9 Mar 2022 Sofien Dhouib, Setareh Maghsudi

Recent advances in domain adaptation establish that requiring a low risk on the source domain and equal feature marginals degrade the adaptation's performance.

Domain Adaptation

Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems

1 code implementation7 Feb 2022 Saeed Ghoorchian, Evgenii Kortukov, Setareh Maghsudi

Our proposed recommender system employs this policy to learn the users' item preferences online while minimizing runtime.

Decision Making Dimensionality Reduction +2

Personalized Education in the AI Era: What to Expect Next?

no code implementations19 Jan 2021 Setareh Maghsudi, Andrew Lan, Jie Xu, Mihaela van der Schaar

The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to ultimately meet her desired goal.

Computation Offloading in Heterogeneous Vehicular Edge Networks: On-line and Off-policy Bandit Solutions

no code implementations14 Aug 2020 Arash Bozorgchenani, Setareh Maghsudi, Daniele Tarchi, Ekram Hossain

Moreover, we demonstrate that the proposed joint base station selection and the relaying mechanism minimize the task loss in a vehicular environment.

Edge-computing

Distributed Uplink Beamforming in Cell-Free Networks Using Deep Reinforcement Learning

no code implementations26 Jun 2020 Firas Fredj, Yasser Al-Eryani, Setareh Maghsudi, Mohamed Akrout, Ekram Hossain

First, we propose a fully centralized beamforming method that uses the deep deterministic policy gradient algorithm (DDPG) with continuous space.

reinforcement-learning Reinforcement Learning (RL)

A Non-Stationary Bandit-Learning Approach to Energy-Efficient Femto-Caching with Rateless-Coded Transmission

no code implementations13 Apr 2020 Setareh Maghsudi, Mihaela van der Schaar

The former problem boils down to a stochastic knapsack problem, and we cast the latter as a multi-armed bandit problem.

Management

Multi-Armed Bandit for Energy-Efficient and Delay-Sensitive Edge Computing in Dynamic Networks with Uncertainty

no code implementations12 Apr 2019 Saeed Ghoorchian, Setareh Maghsudi

The full potential of edge computing becomes realized only if a smart device selects the most appropriate server in terms of the latency and energy consumption, among many available ones.

Edge-computing

Distributed Cell Association for Energy Harvesting IoT Devices in Dense Small Cell Networks: A Mean-Field Multi-Armed Bandit Approach

no code implementations30 Apr 2016 Setareh Maghsudi, Ekram Hossain

In this article, we study the distributed cell association problem for energy harvesting IoT devices in UD-SCNs.

Distributed User Association in Energy Harvesting Small Cell Networks: A Probabilistic Model

no code implementations27 Jan 2016 Setareh Maghsudi, Ekram Hossain

We consider a distributed downlink user association problem in a small cell network, where small cells obtain the required energy for providing wireless services to users through ambient energy harvesting.

Multi-armed Bandits with Application to 5G Small Cells

no code implementations2 Oct 2015 Setareh Maghsudi, Ekram Hossain

This requires the next generation wireless networks to move towards new networking paradigms that are able to efficiently support resource-demanding applications such as personalized mobile services.

Multi-Armed Bandits

Cannot find the paper you are looking for? You can Submit a new open access paper.