Conference Publications
Prepirnts
Conference Papers
- Relative almost sure regret bounds
for certainty equivalence control of Markov Jump
Systems (pdf)
Borna Sayedana, Mohammad Afshari, Aditya Mahajan and Peter Caines
IEEE Conference on Decision and Control (CDC), Singapore, Dec 2023. - Asymmetric Actor Critic with
Approximate Information State (pdf)
Amit Sinha and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Singapore, Dec 2023. - Weighted norm bounds in MDPs with
unbounded per-step cost (pdf)
Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
IEEE Conference on Decision and Control (CDC), Singapore, Dec 2023. - A modified Thompson sampling-based
learning algorithm for unknown linear systems
(pdf)
(slides)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
IEEE Conference on Decision and Control (CDC), Cancun, Mexico, Dec 2022. - Consistency and rate of convergence
of switched least square estimators for autonomous Markov
Jump Linear Systems (pdf)
(slides)
Borna Sayedana, Mohammad Afshari, Peter E. Caines and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Cancun, Mexico, Dec 2022. - Thompson-sampling based
reinforcement learning for networked control of unknown
linear systems (pdf)
(slides)
Borna Sayedana, Mohammad Afshari, Peter E. Caines and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Cancun, Mexico, Dec 2022. - Partially observable restless
bandits with restarts: indexability and computation of
Whittle index (pdf)
Nima Akbarzadeh and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Cancun, Mexico, Dec 2022. - On learning history-based policies
for controlling Markov decision processes
Gandharv Patil, Aditya Mahajan and Doina Precup
Reinforcement Learning and Decision Making (RLDM), Providence, RI, June 2022. - Consistency and rate of convergence
of switched least squares estimator for autonomous switched
linear systems
Borna Sayedana, Mohammad Afshari, Peter E. Caines and Aditya Mahajan
Reinforcement Learning and Decision Making (RLDM), Providence, RI, June 2022. - Robustness of Markov perfect
equilibrium to model approximations in general-sum dynamic
games (pdf)
(slides)
Jayakumar Subramanian, Amit Sinha and Aditya Mahajan
Indian Control Conference, Virtual, 20–22 Dec, 2021. - Thompson Sampling for linear
quadratic mean-field teams (pdf)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
IEEE Conference on Decision and Control (CDC), Virtual, 13–15 Dec, 2021. - Mean-field approximation for
large-population beauty-contest games (pdf)
(slides)
Raihan Seraj, Aditya Mahajan and Jerome Le Ny
IEEE Conference on Decision and Control (CDC), Virtual, 13–15 Dec, 2021. - Decision referrals in
Human-Automation teams (pdf)
(slides)
Kesav Kaza, Aditya Mahajan and Jerome Le Ny
IEEE Conference on Decision and Control (CDC), Virtual, 13–15 Dec, 2021. - Structure-aware reinforcement
learning for node overload protection in mobile edge
computing (pdf)
(video)
Anirudha Jitani, Aditya Mahajan, Zhongwen Zhu, Hatem Abou-zeid, Emannuel T. Fapi and Hakimeh Purmehdi
IEEE International Conference on Communications (ICC), Montreal, Canada, 14–18 Jun, 2021. - Cross-layer communication over
fading channels with adaptive decision feedback
(pdf)
(code)
Borna Sayedana, Aditya Mahajan and Edmund Yeh
International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks (WiOpt), Volos, Greece, 15–19 Jun, 2020. - Restless bandits with controlled
restarts: Indexability and computation of Whittle
index (pdf)
(slides)
(code)
Nima Akbarzadeh and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Nice, France, 11–13 Dec, 2019. - Approximate information state for
partially observed systems (pdf) (slides)
Jayakumar Subramanian and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Nice, France, 11–13 Dec, 2019. - Networked control of coupled
subsystems: Spectral decomposition and low-dimensional
solutions (pdf)
Shuang Gao and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Nice, France, 11–13 Dec, 2019. - Dynamic spectrum access under
partial observations: A restless bandit approach
(pdf)
(slides)
Nima Akbarzadeh and Aditya Mahajan
Canadian Workshop on Information Theory, Hamilton, Ontario, Canada, 2–6 June, 2019. - Approximate information state for
partially observed systems (pdf)
Jayakumar Subramanian and Aditya Mahajan
Reinforcement Learning and Decision Making (RLDM), Montreal, Canada, 7–10 July, 2019. - Reinforcement learning in mean-field
teams (pdf)
Jayakumar Subramanian, Raihan Seraj and Aditya Mahajan
Reinforcement Learning and Decision Making (RLDM), Montreal, Canada, 7–10 July, 2019. - Reinforcement learning in mean-field
teams (pdf)
(poster)
Jayakumar Subramanian, Raihan Seraj and Aditya Mahajan
AAMAS Workshop on Adaptive and Learning Agents, Montreal, Canada, 13-17 May, 2019. - Team optimal decentralized state
estimation (pdf)
(slides)
Mohammad Afshari and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018. - Optimal sampling of multiple linear
processes over a shared medium (pdf)
(slides)
Sebin Mathew, Karl H. Johannson and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018. - On controllability of
leader-follower dynamics over a directed graph
(pdf)
(slides)
Jayakumar Subramanian, Aditya Mahajan and Aditya A. Paranjape
IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018. - Renewal Monte Carlo: Renewal theory
based reinforcement learning (pdf)
(slides)
Jayakumar Subramanian and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018. - Optimal decentralized control of two
agent linear system with partial output feedback: certainty
equivalence and optimality of linear strategies
(pdf)
(poster)
Mohammad Afshari and Aditya Mahajan
IFAC Workshop on Distributed Estimation and Control in Networked Systems, Groningen, Netherlands, Aug 27–28, 2018. - A policy gradient algorithm to
compute boundedly rational stationary mean field
equilibria (pdf)
(poster)
Jayakumar Subramanian and Aditya Mahajan
ICML/IJCAI/AAMAS Workshop on Planning and Learning (PAL-18), Stockholm, Sweden, July 15, 2018. - On privacy in smart metering systems
with periodically time-varying input distribution
(pdf)
(slides)
Yu Liu, Ashish Khisti and Aditya Mahajan
IEEE GlobalSIP Symposium on Control and Information Theoretic Approaches to Privacy and Security, Montreal, Canada, Nov 14–16, 2017. - Remote estimation over control area
networks (pdf)
(slides)
Aditya Mahajan
IEEE Vehicular Technology Conference (VTC), Networked Vehicles for Intelligent Transportation and Smart Grids (NetV) Workshop, Toronto, Canada, Sep 24–27, 2017. - Static teams with common
information (pdf)
(slides)
Mohammad Afshari and Aditya Mahajan
IFAC World Congress, Toulouse, France, July 9–14, 2017. - Structure of optimal strategies for
remote estimation over Gilbert-Elliott channel with
feedback (pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
IEEE International Symposium on Information Theory (ISIT), Aachen, Germany, June 25–30, 2017. - Stochastic approximation based
methods for computing the optimal thresholds in
remote-state estimation with packet drops
(pdf)
(slides)
Jhelum Chakravorty, Jayakumar Subramanian and Aditya Mahajan
American Control Conference (ACC), Seattle, WA, May 24–26, 2017. - Multi-Armed Bandits for Efficient
Lifetime Estimation in MPSoC design (pdf)
(slides)
Calvin Ma, Aditya Mahajan and Brett Meyer
Design, Automation and Test in Europe (DATE), Laussane, Switzerland, March 27–31, 2017. - Remote-state estimation with packet
drop (pdf)
(poster)
Jhelum Chakravorty and Aditya Mahajan
IFAC Workshop on Distributed Estimation and Control in Networked Systems, Tokyo, Japan, Sep 8–9, 2016.
Recipient of the Best Student Paper Award. - Structural results for two-user
interactive communication (pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
IEEE International Symposium on Information Theory (ISIT), Barcelona, Spain, July 10–15, 2016. - Privacy-optimal strategies for smart
metering systems with a rechargeable battery
(pdf)
(slides)
Simon Li, Ashish Khisti and Aditya Mahajan
American Control Conference (ACC), Boston, MA, July 6–8, 2016. - Privacy preserving rechargeable
battery policies for smart metering systems
(pdf)
(slides)
Simon Li, Ashish Khisti and Aditya Mahajan
International Zurich Seminar on Communications, Zurich, Switzerland, March 2–4, 2016. - Team-optimal solution of finite
number of mean-field coupled LQG subsystems
(pdf)
Jalal Arabneydi and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Osaka, Japan, Dec 15-18, 2015. - On computing optimal thresholds in
decentralized sequential hypothesis testing
(pdf)
(slides)
Can Cui and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), Osaka, Japan, Dec 15-18, 2015. - Reinforcement learning in
decentralized stochastic control systems with partial
history sharing (pdf)
(slides)
Jalal Arabneydi and Aditya Mahajan
American Control Conference (ACC), pp. 5449–5456, Chicago, IL, Jul 1–3, 2015. - Structure of optimal
privacy-preserving policies in smart-metered systems with a
rechargeable battery (pdf)
(poster)
Simon Li, Ashish Khisti and Aditya Mahajan
IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp. 375--379, Stockholm, Sweden, June 28–July 1, 2015. - Distortion-transmission trade-off in
real-time transmission of Gauss-Markov sources
(pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
IEEE International Symposium on Information Theory (ISIT), Hong Kong, China, June 14-19, 2015. - Reinforcement Learning in
Multi-Agent Systems with Partial History Sharing
(pdf)
Jalal Arabneydi and Aditya Mahajan
Reinforcement Learning and Decision Making (RLDM), Edmonton, AL, Jun 7-10, 2015. - An estimation based allocation rule
with super-linear regret and finite lock-on time for
time-dependent multi-armed bandit processes
(pdf)
(slides)
Prokopis Prokopiou, Peter Caines and Aditya Mahajan
Canadian Conference on Elecrtical and Computer Engineering (CCECE), pp. 1299–1306, Halifax, NS, May 3-6, 2015. - Distortion-transmission trade-off in
real-time transmission of Markov sources (pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
Information Theory Workshop (ITW), pp. 1--5, Jerusleum, Israel, Apr 26–May 1, 2015. - Team optimal control of coupled
major-minor subsystems with mean field sharing
(pdf)
(slides)
Jalal Arabneydi and Aditya Mahajan
Indian Control Conference, pp. 95-100, Chennai, India, Jan 6-7, 2015. - On the optimal thresholds in remote
state estimation with communication costs
(pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), pp. 1041–1046, Los Angeles, CA, Dec 15-17, 2014. - Team optimal control of coupled
subsystems with mean field sharing (pdf)
(slides)
Jalal Arabneydi and Aditya Mahajan
IEEE Conference on Decision and Control (CDC), pp. 1669–1674, Los Angeles, CA, Dec 15-17, 2014.
Recipient of the Best Student Paper Award. - Average cost optimal threshold
strategies for remote state estimation with communication
costs (pdf)
(slides)
Jhelum Chakravorty and Aditya Mahajan
Allerton conference on communication, control, and computing, Monticello, IL, Oct 1-3, 2014. - Simultaneous real-time communication
of multiple Markov sources over a shared channel
(pdf)
(slides)
Mehnaz Mannan and Aditya Mahajan
IEEE International Symposium on Information Theory (ISIT), pp. 2356–2360, Honolulu, HI, Jun 29-July 4, 2014. - Static LQG teams with countably
infinite players (pdf)
Aditya Mahajan, Nuno C. Martins and Serdar Yüksel
IEEE Conference on Decision and Control (CDC), Florence, Italy, Dec 10-13, 2013. - Structure of optimal policies in
active sensing (pdf)
(slides)
Aditya Mahajan
37th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5265-5268, Kyoto, Japan, March 25-30, 2012. - Optimal decentralized control of
coupled subsystems with control sharing (pdf)
(slides)
Aditya Mahajan
50th IEEE Conference on Decision and Control (CDC), pp. 5726-5731, Orlando, FL, Dec 12-15, 2011. - Optimal transmission policies for
two-user multiple access broadcast using dynamic team
theory (pdf)
(slides)
Aditya Mahajan
48th Allerton conference on communication, control, and computing, pp. 806-813, Monticello, IL, Sep 29-Oct 1, 2010. - Measure and cost dependent
properties of information structures (pdf)
(slides)
Aditya Mahajan and Serdar Yüksel
American Control Conference (ACC), pp. 6397-6402, Baltimore, MD, June 30-July 2, 2010. - A structural result for delayed
sharing information structures (pdf)
Ashutosh Nayyar, Aditya Mahajan and Demosthenis Teneketzis
American Control Conference (ACC), pp. 6391-6396, Baltimore, MD, June 30-July 2, 2010. - Opportunistic capacity and error
exponent regions for compound channel with
feedback (pdf)
(slides)
Aditya Mahajan and Sekhar Tatikonda
IEEE International Symposium on Information Theory (ISIT), pp. 236-240, Austin, TX, June 13-18, 2010. - Opportunistic capacity and error
exponent regions for variable length communication over
compound channel with feedback (pdf)
(slides)
Aditya Mahajan and Sekhar Tatikonda
44th Conference on Information Sciences and Systems (CISS), pp. 1–6, Princeton, NJ, March 17-19, 2010. - Optimal sequential transmission over
degraded broadcast channels with nested feedback
(pdf)
(slides)
Aditya Mahajan
47th Allerton conference on communication, control, and computing, pp. 795-802, Monticello, IL, Sep 30-Oct 2, 2009. - Sequential team form and its
simplification using graphical models (pdf)
(slides)
Aditya Mahajan and Sekhar Tatikonda
47th Allerton conference on communication, control, and computing, pp. 330-339, Monticello, IL, Sep 30-Oct 2, 2009. - A training based scheme for
communicating over unknown channels with feedback
(pdf)
(slides)
Aditya Mahajan and Sekhar Tatikonda
47th Allerton conference on communication, control, and computing, pp. 1549-1553, Monticello, IL, Sep 30-Oct 2, 2009. - A graphical modeling approach to
simplifying sequential teams (pdf)
(slides)
Aditya Mahajan and Sekhar Tatikonda
7th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), Control over Communication Channels (ConCom) Workshop, pp. 1–8, Seoul, South Korea, June 27, 2009. - Identifying tractable decentralized
problems on the basis of information structures
(pdf)
(slides)
Aditya Mahajan, Ashutosh Nayyar and Demosthenis Teneketzis
46th Allerton conference on communication, control, and computing, pp. 1440-1449, Monticello, IL, Sep 23-26, 2008. - Initial analyses and demonstration of
soil moisture smart sensor web (pdf)
Mahta Moghaddam, Dara Entekhabi, Leila Farhadi, Yuriy Goykhman, Mingyan Liu, Aditya Mahajan, Ashutosh Nayyar, David Shuman and Demosthenis Teneketzis
Earth Science Technology Conference (ESTC), pp. 1–8, East Alephi, MD, June 24-26, 2008. - On time diagnosis of discrete event
systems (pdf)
(slides)
Aditya Mahajan and Demosthenis Teneketzis
9th International Workshop on Discrete Event Systems (WODES), pp. 382-387, Gothenburg, Sweden, May 28-30, 2008. - Real-time communication systems with
noisy feedback (pdf)
(slides)
Aditya Mahajan and Demosthenis Teneketzis
IEEE Information Theory Workshop (ITW), pp. 283-287, Lake Tahoe, CA, Sep 13-15, 2007. - Optimal performance of feedback
control systems with limited communication over noisy
channels (pdf)
(slides)
Aditya Mahajan and Demosthenis Teneketzis
45th IEEE Conference on Decision and Control (CDC), pp. 3228-3235, San Diego, CA, Dec 13-15, 2006. - Fixed delay optimal joint
source-channel coding for finite-memory systems
(pdf)
(slides)
Aditya Mahajan and Demosthenis Teneketzis
IEEE International Symposium on Information Theory (ISIT), pp. 2319-2323, Seattle, WA, July 9-14, 2006. - A decision theoretic approach to
real-time communication (pdf)
(slides)
Aditya Mahajan and Demosthenis Teneketzis
43rd Allerton conference on communication, control, and computing, pp. 1–10, Monticello, IL, Sep 28-30, 2005.
Disclaimer
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.