Publications
Journal Papers
- On Model-Free Learning over Rate-Limited Channels: The Linear Quadratic Regulator Case
Lintao Ye, Aritra Mitra, and Vijay Gupta
Automatica, 2026 [arXiv] - Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling
Feng Zhu, Aritra Mitra, and Robert W. Heath
Transactions on Machine Learning Research (TMLR), 2026 [Link] - Model-free learning with heterogeneous dynamical systems: A federated LQR approach
Han Wang, Leonardo F. Toso, Aritra Mitra, and James Anderson
Transactions on Machine Learning Research (TMLR), 2026 [arXiv] - Finite-Time Analysis of Over-the-Air Federated TD Learning
Nicolo Dal Fabbro, Aritra Mitra, Robert W. Heath, Luca Schenato, George J. Pappas
IEEE Transactions on Wireless Communications (TWC), 2025 [Link] - A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation
Aritra Mitra
IEEE Transactions on Automatic Control (TAC), 2025. [arXiv] [Link] - Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity [arXiv]
Han Wang, Aritra Mitra, Hamed Hassani, George J. Pappas, and James Anderson
Transactions on Machine Learning Research (TMLR), 2024. [Link] - Temporal Difference Learning with Compressed Updates: Error-Feedback Meets Reinforcement Learning
Aritra Mitra, George J. Pappas, and Hamed Hassani
Transactions on Machine Learning Research (TMLR), 2024. [Link]
(Received Journal to Conference Certification for ICML 2026) - A Survey of Graph-Theoretic Approaches for Analyzing the Resilience of Networked Control Systems
Mohammad Pirani, Aritra Mitra, and Shreyas Sundaram
Automatica, 2023. [arXiv] - Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling
Nicolo Dal Fabbro, Aritra Mitra and George Pappas
IEEE Control Systems Letters, 2023. [arXiv] - Distributed State Estimation over Time-Varying Graphs: Exploiting the Age-of-Information
Aritra Mitra, John A. Richards, Saurabh Bagchi and Shreyas Sundaram
IEEE Transactions on Automatic Control, 2022. [arXiv] [ieeeexplore] - On the Computational Complexity of the Secure State-Reconstruction Problem
Yanwen Mao, Aritra Mitra, Shreyas Sundaram and Paulo Tabuada
Automatica, 2022. [arXiv] [link] - Distributed Inference with Sparse and Quantized Communication
Aritra Mitra, John A. Richards, Saurabh Bagchi and Shreyas Sundaram
IEEE Transactions on Signal Processing, 2021. [arXiv] [ ieeeexplore ] - On the Impacts of Redundancy, Diversity, and Trust in Resilient Distributed State Estimation
Aritra Mitra, Faiq Ghawash, Shreyas Sundaram and Waseem Abbas
IEEE Transactions on Control of Network Systems, 2020. [ieeeexplore] - A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience
Aritra Mitra, John A. Richards and Shreyas Sundaram
IEEE Transactions on Automatic Control, 2020. [arXiv] [ ieeeexplore ] - Byzantine-Resilient Distributed Observers for LTI Systems
Aritra Mitra and Shreyas Sundaram
Automatica, 2019. [arXiv] [ link ] - Resilient Distributed State Estimation with Mobile Agents: Overcoming Byzantine Adversaries, Communication Losses, and Intermittent Measurements
Aritra Mitra, John A. Richards, Saurabh Bagchi and Shreyas Sundaram
Autonomous Robots: Special Issue on Foundations of Resilience for Networked Robotic Systems, 2019. [link] - Distributed Observers for LTI Systems
Aritra Mitra and Shreyas Sundaram
IEEE Transactions on Automatic Control, 2018. [pdf] [ ieeeexplore ]
Peer-Reviewed Conference Papers
- Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
Sreejeet Maity and Aritra Mitra
43rd International Conference on Machine Learning (ICML), 2026, Seoul, South Korea [arXiv] - A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
Feng Zhu, Robert W. Heath, and Aritra Mitra
43rd International Conference on Machine Learning (ICML), 2026, Seoul, South Korea [arXiv] - Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
Vinay Kanakeri, Shivam Bajaj, Ashwin Verma, Vijay Gupta, and Aritra Mitra
8th Annual Learning for Dynamics & Control Conference (L4DC), 2026, USC [arXiv] - Robust Federated Q-Learning with Almost No Communication
Sreejeet Maity and Aritra Mitra
American Control Conference (ACC), 2026, New Orleans, USA - Variance-Reduced Q-Learning over Static and Time-Varying Networks
Sreejeet Maity*, Feng Zhu*, Aritra Mitra, and Robert W. Heath
American Control Conference (ACC), 2026, New Orleans, USA - Boosting-Enabled Robust System Identification of Partially Observed LTI Systems Under Heavy-Tailed Noise
Vinay Kanakeri and Aritra Mitra
64th IEEE Decision and Control Conference (CDC), 2025, Rio De Janeiro, Brazil [arXiv] - Outlier-Robust Linear System Identification under Heavy-tailed Noise
Vinay Kanakeri and Aritra Mitra
7th Annual Learning for Dynamics & Control Conference (L4DC), 2025, Michigan, Ann Arbor [arXiv] - Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits
Sreejeet Maity and Aritra Mitra
28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025, Mai Khao, Thailand [arXiv] - Robust Q-Learning under Corrupted Rewards
Sreejeet Maity and Aritra Mitra
63rd IEEE Decision and Control Conference (CDC), 2024, Milan, Italy - Towards Fast Rates for Federated and Multi-Task Reinforcement Learning
Feng Zhu, Robert W. Heath, and Aritra Mitra
63rd IEEE Decision and Control Conference (CDC), 2024, Milan, Italy - DASA: Delay-Adaptive Multi-Agent Stochastic Approximation
Nicolò Dal Fabbro*, Arman Adibi*, H. Vincent Poor, Sanjeev R. Kulkarni, Aritra Mitra, and George J. Pappas
63rd IEEE Decision and Control Conference (CDC), 2024, Milan, Italy - On the Convergence of Policy Gradient for Designing a Linear Quadratic Regulator by Leveraging a Proxy System
Lintao Ye, Aritra Mitra, and Vijay Gupta
63rd IEEE Decision and Control Conference (CDC), 2024, Milan, Italy - Towards Model-Free LQR Control over Rate-Limited Channels
Aritra Mitra*, Lintao Ye*, and Vijay Gupta
6th Annual Learning for Dynamics & Control Conference (L4DC), 2024, Oxford, UK. [arXiv]
(Selected for Oral Presentation, Top 7.5%) - Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling
Arman Adibi*, Nicolò Dal Fabbro*, Luca Schenato, Sanjeev Kulkarni, H. Vincent Poor, George J. Pappas, Hamed Hassani, and Aritra Mitra
27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024, Valencia, Spain. [arXiv] - Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Chenyu Zhang, Han Wang, Aritra Mitra, and James Anderson
12th International Conference on Learning Representations (ICLR), 2024, Vienna, Austria. [Link] - Min-Max Optimization under Delays
Arman Adibi, Aritra Mitra, and Hamed Hassani
American Control Conference (ACC), 2024, Toronto, Canada. [arXiv] - Finite-Time Analysis of Asynchronous Multi-Agent TD Learning
Nicolò Dal Fabbro, Arman Adibi, Aritra Mitra, and George J. Pappas
American Control Conference (ACC), 2024, Toronto, Canada. - Linear Stochastic Bandits over a Bit-Constrained Channel
Aritra Mitra, Hamed Hassani, and George J. Pappas
5th Annual Learning for Dynamics and Control Conference (L4DC), 2023,
Philadelphia, USA. [arXiv]
(One of 16/167 papers selected for Oral Presentation) - Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
Aritra Mitra*, Arman Adibi*, George J. Pappas, and Hamed Hassani
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. [arXiv] - Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
Arman Adibi*, Aritra Mitra*, George J. Pappas, and Hamed Hassani
61st IEEE Decision and Control Conference (CDC), 2022, Cancun, Mexico. [arXiv] - Distributed Hypothesis Testing and Social Learning in Finite Time with a Finite Amount of Communication
Shreyas Sundaram and Aritra Mitra
61st IEEE Decision and Control Conference (CDC), 2022, Cancun, Mexico. - Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
Aritra Mitra, Rayana Jaafar, George J. Pappas and Hamed Hassani
Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021. [arXiv] [Link] [Poster] [Talk at Google FL Workshop] - Online Federated Learning
Aritra Mitra, Hamed Hassani, and George J. Pappas
60th IEEE Decision and Control Conference (CDC), 2021, Austin, Texas, USA. - Federated Learning with Incrementally Aggregated Gradients
Aritra Mitra*, Rayana Jaafar*, George J. Pappas and Hamed Hassani
60th IEEE Decision and Control Conference (CDC), 2021, Austin, Texas, USA. - Near-Optimal Data Source Selection for Bayesian Learning
Lintao Ye, Aritra Mitra and Shreyas Sundaram
3rd Annual Learning for Dynamics and Control Conference (L4DC), 2021, ETH Zurich, Switzerland. [arXiv] - Event-Triggered Distributed Inference
Aritra Mitra, Saurabh Bagchi and Shreyas Sundaram
59th IEEE Decision and Control Conference (CDC), 2020, Jeju Island, Republic of Korea. - A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks
Aritra Mitra, John A. Richards and Shreyas Sundaram
58th IEEE Decision and Control Conference (CDC), 2019, Nice, France. [arXiv] - When is the Secure State-Reconstruction Problem Hard?
Yanwen Mao, Aritra Mitra, Shreyas Sundaram and Paulo Tabuada
58th IEEE Decision and Control Conference (CDC), 2019, Nice, France. - A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience
Aritra Mitra, John A. Richards and Shreyas Sundaram
American Control Conference (ACC), 2019, Philadelphia, USA. [arXiv] - Finite-Time Distributed State Estimation over Time-Varying Graphs: Exploiting the Age-of-Information
Aritra Mitra, John A. Richards, Saurabh Bagchi and Shreyas Sundaram
American Control Conference (ACC), 2019, Philadelphia, USA. [arXiv] - A Novel Switched Linear Observer for Estimating the State of a Dynamical Process with a Mobile Agent
Aritra Mitra and Shreyas Sundaram
57th IEEE Decision and Control Conference (CDC), 2018, Miami, USA. [pdf] - On the Impact of Trusted Nodes in Resilient Distributed State Estimation of LTI Systems
Aritra Mitra, Waseem Abbas and Shreyas Sundaram
57th IEEE Decision and Control Conference (CDC), 2018, Miami, USA. - Secure Distributed State Estimation of an LTI System over Time-Varying Networks and Analog Erasure Channels
Aritra Mitra and Shreyas Sundaram
American Control Conference (ACC), 2018, Milwaukee, USA. [pdf] - Distributed Functional Observers for LTI Systems
Aritra Mitra and Shreyas Sundaram
56th IEEE Decision and Control Conference (CDC), 2017, Melbourne, Australia. [pdf] - Secure Distributed Observers for a Class of Linear Time Invariant Systems in the presence of Byzantine Adversaries
Aritra Mitra and Shreyas Sundaram
55th IEEE Decision and Control Conference (CDC), 2016, Las Vegas, NV, USA. [pdf] - An Approach for Distributed State Estimation of LTI Systems
Aritra Mitra and Shreyas Sundaram
54th Annual Allerton Conference, 2016, IL, USA. [pdf] - Control of a 4 DOF Barrett WAM Robot: Modeling, Control Synthesis and Experimental Validation
Aritra Mitra, Niladri Das, Raj Nayan Samant, and Laxmidhar Behera
1st IEEE International Conferance on Control, Measurement and Instrumentation (CMI), 2016, Kolkata, India. - Continuous-Time Single Network Adaptive Critic based Optimal Sliding Mode Control for Nonlinear Control Affine Systems
Aritra Mitra and Laxmidhar Behera
34th Chinese Control Conference (CCC), 2015, Hangzhou, China. - Development of a Fuzzy Sliding Mode Controller with Adaptive Tuning Technique for a MRI Guided Robot in the Human Vasculature
Aritra Mitra and Laxmidhar Behera
13th IEEE International Conference on Industrial Informatics (INDIN), 2015, Cambridge, UK.
* Denotes equal contribution