About

S. Rasoul Etesami is an Associate Professor in the Department of Industrial and Systems Engineering (ISE) at the University of Illinois Urbana-Champaign. He is also affiliated with the Department of Electrical and Computer Engineering (ECE) and the Coordinated Science Laboratory (CSL) at the same university, where he is a member of the Decision and Control group. His research is centered around understanding and analyzing the complex behaviors in multiagent decision-making systems using tools from control theory, game theory, machine learning, and optimization. Etesami received his Ph.D. in Electrical and Computer Engineering from the University of Illinois Urbana-Champaign in December 2015, during which he spent a summer as a Research Intern at Alcatel-Lucent Bell Labs. He has held positions as a Postdoctoral Research Fellow at Princeton University and WINLAB, and has been recognized with support from the US National Science Foundation CAREER Award and the US Air Force Young Investigator Award. His academic career includes roles as an Assistant Professor and now as an Associate Professor at Illinois, with ongoing affiliations with the Department of Electrical and Computer Engineering and the Coordinated Science Laboratory. His research interests include multiagent network systems, game theory and distributed optimization, socioeconomic behaviors and dynamics, and learning in cyber-physical systems.

Research topics

• Computer Science
• Machine Learning
• Data Mining
• Econometrics
• Artificial Intelligence
• Computer Security
• Economics
• Mathematics
• Mathematical optimization
• Operations management
• Mathematical economics
• Statistics
• Physics

Selected publications

• F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data

  arXiv (Cornell University) · 2024 · 1 citations

  • Computer Science
  • Econometrics
  • Machine Learning

  Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a significant challenge for traditional forecasting methods. In this paper, we propose a novel approach that leverages strategically chosen proxy data reflective of potential sales patterns from similar entities during non-peak periods, enriched by features learned from a graph neural networks (GNNs)-based forecasting model, to predict demand during peak events. We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm that leverages proxy data from non-peak periods and GNN-generated relational metadata to learn feature-specific layer parameters, thereby adapting to demand forecasts for peak events. Theoretically, we show that by considering domain similarities through task-specific metadata, our model achieves improved generalization, where the excess risk decreases as the number of training tasks increases. Empirical evaluations on large-scale industrial datasets demonstrate the superiority of our approach. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.

  DOI

• FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning

  arXiv (Cornell University) · 2024

  • Computer Science
  • Data Mining
  • Computer Science

  The performance of Transfer Learning (TL) heavily relies on effective pretraining, which demands large datasets and substantial computational resources. As a result, executing TL is often challenging for individual model developers. Federated Learning (FL) addresses these issues by facilitating collaborations among clients, expanding the dataset indirectly, distributing computational costs, and preserving privacy. However, key challenges remain unresolved. First, existing FL methods tend to optimize transferability only within local domains, neglecting the global learning domain. Second, most approaches rely on indirect transferability metrics, which do not accurately reflect the final target loss or true degree of transferability. To address these gaps, we propose two enhancements to FL. First, we introduce a client-server exchange protocol that leverages cross-client Jacobian (gradient) norms to boost transferability. Second, we increase the average Jacobian norm across clients at the server, using this as a local regularizer to reduce cross-client Jacobian variance. Our transferable federated algorithm, termed FedGTST (Federated Global Transferability via Statistics Tuning), demonstrates that increasing the average Jacobian and reducing its variance allows for tighter control of the target loss. This leads to an upper bound on the target loss in terms of the source loss and source-target domain discrepancy. Extensive experiments on datasets such as MNIST to MNIST-M and CIFAR10 to SVHN show that FedGTST outperforms relevant baselines, including FedSR. On the second dataset pair, FedGTST improves accuracy by 9.8% over FedSR and 7.6% over FedIIR when LeNet is used as the backbone.

  PublisherOA PDFDOI

• Striking a Balance: An Optimal Mechanism Design for Heterogenous Differentially Private Data Acquisition for Logistic Regression

  arXiv (Cornell University) · 2023

  • Computer Science
  • Computer Science
  • Data Mining

  We address the challenge of solving machine learning tasks using data from privacy-sensitive sellers. Since the data is private, we design a data market that incentivizes sellers to provide their data in exchange for payments. Therefore our objective is to design a mechanism that optimizes a weighted combination of test loss, seller privacy, and payment, striking a balance between building a good privacy-preserving ML model and minimizing payments to the sellers. To achieve this, we first propose an approach to solve logistic regression with known heterogeneous differential privacy guarantees. Building on these results and leveraging standard mechanism design theory, we develop a two-step optimization framework. We further extend this approach to an online algorithm that handles the sequential arrival of sellers.

  PublisherOA PDFDOI

Frequent coauthors

• R. Srikant

  University of Illinois Urbana-Champaign

  26 shared

• Venugopal V. Veeravalli

  University of Illinois Urbana-Champaign

  25 shared

• Bronwyn H. Bradshaw‐Hajek

  University of South Australia

  25 shared

• Ms Mccullough

  University of Illinois Urbana-Champaign

  25 shared

• Zhongming Zhao

  25 shared

• Ms Alred

  University of Southern California

  25 shared

• Sean Meyn

  University of Florida

  25 shared

• N. Minh

  VinUniversity

  25 shared

Awards & honors

• IEEE Transactions on Control of Network Systems (TCNS) Best…
• Automatica Best Paper Award (2017)
• IEEE Transactions on Control of Network Systems (TCNS) Best…
• IEEE Transactions on Automatic Control (TAC) Best Paper Awar…
• IEEE Control Systems Letters (L-CSS) Best Paper Award (2020)

Similar researchers at University of Illinois Urbana-Champaign

• Jiawei Hanh-146
• Maria T. Grosse Perdekamph-141
• Gan Zhangh-134
• Jeffrey S. Mooreh-130
• Shuming Nieh-128