Publications
Journal Articles
Learning Multi-Robot Coordination through Locality-Based Factorized Multi-Agent Actor-Critic Algorithm
IEEE Robotics and Automation Letters (RAL), 2025
Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Transactions on Machine Learning Research (TMLR), Jan 2025
Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks
Transactions on Machine Learning Research (TMLR), Oct 2024
A Survey on the Possibilities & Impossibilities of AI-Generated Text Detection
Transactions on Machine Learning Research (TMLR), Jan 2024
On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control
Journal of Machine Learning Research (JMLR), Jan 2024
Efficient Gaussian Process Bandits by Believing only Informative Actions
IEEE Transactions on Artificial Intelligence (TAI), Sep 2023
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
Journal of Artificial Intelligence Research (JAIR), Nov 2023
Projection-Free Algorithm for Stochastic Bi-level Optimization
IEEE Transactions on Signal Processing (TSP), Nov 2022
Escaping Saddle Points with the Successive Convex Approximation Algorithm
IEEE Transactions on Signal Processing (TSP), Nov 2021
Approximate Shannon Sampling in Importance Sampling: Nearly Consistent Finite Particle Estimates
IEEE Transactions on Signal Processing (TSP), Sep 2021
Cautious Reinforcement Learning via Distributional Risk in the Dual Domain
IEEE Journal on Selected Areas in Information Theory (JSAIT), vol. 2, no. 2, pp. 611–626, Jun 2021
Conservative Stochastic Optimization with Expectation Constraints
IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 3190–3205, May 2021
Adaptive Kernel Learning in Heterogeneous Networks
IEEE Transactions on Signal and Information Processing over Networks (TSIPN), Feb 2021
Dynamic Online Learning via Frank-Wolfe Algorithm
IEEE Transactions on Signal Processing (TSP), Dec 2020
Online Learning over Dynamic Graphs via Distributed Proximal Gradient Algorithm
IEEE Transactions on Automatic Control (TAC), Nov 2021
Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
IEEE Transactions on Communications (TCOM), Sep 2020
Asynchronous and Parallel Distributed Pose Graph Optimization
IEEE Robotics and Automation Letters (RAL), Feb 20202020 Honorable Mention
GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning
Journal of Machine Learning Research (JMLR), Mar 2020
Optimally Compressed Nonparametric Online Learning
IEEE Signal Processing Magazine (SPM) — Special Issue on Distributed, Streaming Machine Learning, May 2020
Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments
IEEE Transactions on Signal Processing (TSP), Jul 2020
Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning
IEEE Transactions on Signal Processing (TSP), Dec 2020
Asynchronous Online Learning in Multi-Agent Systems with Proximity Constraints
IEEE Transactions on Signal and Information Processing over Networks (TSIPN), vol. 5, no. 3, pp. 479–494, Sep 2019
Online Learning with Inexact Proximal Online Gradient Descent Algorithms
IEEE Transactions on Signal Processing (TSP), vol. 67, no. 5, pp. 1338–1352, Mar 2019
Asynchronous Saddle Point Algorithm for Stochastic Optimization in Heterogeneous Networks
IEEE Transactions on Signal Processing (TSP), vol. 67, no. 7, pp. 1742–1757, Apr 2019
Asynchronous Incremental Stochastic Dual Descent Algorithm for Network Resource Allocation
IEEE Transactions on Signal Processing (TSP), vol. 66, no. 9, pp. 2229–2244, May 2018
Online Algorithms for Storage Utilization under Real-Time Pricing in Smart Grid
International Journal of Electrical Power and Energy Systems (JEPES), vol. 101, Mar 2018
Tracking Moving Agents via Inexact Online Gradient Descent Algorithm
IEEE Journal of Selected Topics in Signal Processing (JSTSP) — Special Issue on ML for Cognition in Radio Communications, vol. 12, no. 1, pp. 202–217, Feb 2018
Network Resource Allocation via Stochastic Subgradient Descent: Convergence Rate
IEEE Transactions on Communications (TCOM), vol. 66, no. 5, pp. 2107–2121, May 2018
BER-Optimized Precoders for OFDM Systems with Insufficient Cyclic Prefix
IEEE Communications Letters, vol. 20, no. 2, pp. 280–283, Feb 2016
Conference Papers
Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA
On the Sample Complexity Bounds of Bilevel Reinforcement Learning
Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA
On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
EfficientEQA: An Efficient Approach to Open Vocabulary Embodied Question Answering for Robotic Assistants
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
On the Vulnerability of LLM/VLM-Controlled Robotics
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robotic Navigation
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
International Conference on Machine Learning (ICML 2025), Vancouver, CA
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
Conference on Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN
Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
AAAI Conference on Artificial Intelligence (AAAI 2025), Philadelphia, USA
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Advances in Neural Information Processing Systems (NeurIPS 2024), Vancouver, CA
Transfer Q*: Principled Decoding for LLM Alignment
Advances in Neural Information Processing Systems (NeurIPS 2024), Vancouver, CA
When, What, and with Whom to Communicate: Enhancing RL-based Multi-Robot Navigation through Selective Communication
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), Abu Dhabi, UAE
LANCAR: Leveraging Language for Context-Aware Robot Locomotion in Unstructured Environments
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), Abu Dhabi, UAE
TrustNavGPT: Trust-Driven Audio-Guided Robot Navigation under Uncertainty with Large Language Models
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), Abu Dhabi, UAEOral
Global Optimality without Mixing Time Oracles in Average-Reward RL via Multi-level Actor-Critic
International Conference on Machine Learning (ICML 2024), Vienna, Austria
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
International Conference on Machine Learning (ICML 2024), Vienna, Austria
MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences
International Conference on Machine Learning (ICML 2024), Vienna, Austria
On the Possibilities of AI-Generated Text Detection
International Conference on Machine Learning (ICML 2024), Vienna, Austria
Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
International Conference on Machine Learning (ICML 2024), Vienna, AustriaSpotlight — Top 3.5%
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning
International Conference on Learning Representations (ICLR 2024), Vienna, Austria
iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning
Conference on Robot Learning (CoRL 2023), Atlanta, GAOral
Bi-Level Nonstationary Kernels for Online Gaussian Process Regression
IEEE International Conference on Automation Science and Engineering (CASE 2023)
STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning
International Conference on Machine Learning (ICML 2023), Honolulu, HI
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic
International Conference on Machine Learning (ICML 2023), Honolulu, HI
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda
Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization
IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK
RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments
IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK
Decentralized Multi-agent Exploration with Limited Inter-agent Communications
IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm
AAAI Conference on Artificial Intelligence (AAAI 2023), Washington DC
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
AAAI Conference on Artificial Intelligence (AAAI 2023), Washington DC
Convergence Rates of Average-Reward Multi-Agent Reinforcement Learning via Randomized Linear Programming
IEEE Conference on Decision and Control (CDC 2022), Cancun, Mexico
HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm
Conference on Robot Learning (CoRL 2022), Auckland, New Zealand
Fast Distributed Beamforming without Receiver Feedback
56th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA
Distributed Riemannian Optimization with Lazy Communication for Collaborative Geometric Estimation
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan
DC-MRTA: Decentralized Multi-Robot Task Allocation and Navigation in Complex Environments
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning
International Conference on Machine Learning (ICML 2022), Baltimore, USA
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
International Conference on Machine Learning (ICML 2022), Baltimore, USA
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
AAAI Conference on Artificial Intelligence (AAAI 2022), Vancouver, Canada
MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
AAAI Conference on Artificial Intelligence (AAAI 2022), Vancouver, Canada
Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent
IEEE Global Communications Conference (Globecom 2021), Madrid, Spain
Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning
55th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA
Intermittent Communications in Decentralized Shadow Reward Actor-Critic
IEEE Conference on Decision and Control (CDC 2021), Nice, France
Wasserstein-Splitting Gaussian Process Regression for Heterogeneous Online Bayesian Inference
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
On the Convergence Theory of Online Bayesian Nonparametric Estimators with Adaptive Hyperparameters
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
Variational Policy Gradient Method for Reinforcement Learning with General Utilities
Advances in Neural Information Processing Systems (NeurIPS 2020), Vancouver, CASpotlight — Top 4%
Joint Position and Beamforming Control via Alternating Nonlinear Least-Squares with a Hierarchical Gamma Prior
American Control Conference (ACC 2021)
Beyond Cumulative Returns via Reinforcement Learning over State-Action Occupancy Measures
American Control Conference (ACC 2021)
Conservative Stochastic Optimization: O(T⁻¹/²) Optimality Gap with Zero Constraint Violation
American Control Conference (ACC 2021)
Conservative Multi-agent Online Kernel Learning in Heterogeneous Networks
54th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA
Asynchronous and Parallel Distributed Pose Graph Optimization
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020), Las Vegas, NV
Efficient Large-Scale Gaussian Process Bandits by Believing only Informative Actions
Learning for Dynamics and Control (L4DC 2020), UC Berkeley, CA
A Projection Operator to Balance Consistency and Complexity in Importance Sampling
NeurIPS Symposium on Advances in Approximate Bayesian Inference, Vancouver, CA
Projection Free Dynamic Online Learning
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), Barcelona, Spain
Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), Barcelona, Spain
Nonparametric Dynamic Online Learning
American Control Conference (ACC 2020), Denver, CO
Approximate Shannon Sampling in Importance Sampling
53rd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA
Nonstationary Nonparametric Optimization: Online Kernel Learning against Dynamic Comparators
International Conference on Continuous Optimization (ICCOPT 2019), Berlin, Germany
Compressed Online Non-parametric Learning
Learning for Dynamics and Control (L4DC 2019), MIT, Cambridge, MA
Online Learning over Time-varying Graphs via Proximal Gradient Descent
IEEE Conference on Decision and Control (CDC 2019), Nice, France
Controlling the Bias-Variance Tradeoff via Coherent Risk for Robust Learning with Kernels
American Control Conference (ACC 2019), Philadelphia, PA
On Socially Optimal Traffic Flow in the Presence of Random Users
IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS 2018), Indore, India
Exact Nonparametric Decentralized Online Optimization
IEEE Global Conference on Signal and Information Processing (GlobalSIP 2018), Anaheim, CA
Time Varying Optimization via Inexact Proximal Online Gradient Descent
52nd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA
Decentralized Asynchronous Stochastic Gradient Descent: Convergence Rate Analysis
International Conference on Signal Processing and Communications (SPCOM 2018), Bangalore, India
Asynchronous Saddle Point Method: Interference Management Through Pricing
IEEE Conference on Decision and Control (CDC 2018)
Adversarial Multi-Agent Target Tracking with Inexact Online Gradient Descent
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), Calgary, Canada
Wireless Network Optimization via Stochastic Sub-gradient Descent: Rate Analysis
IEEE International Conference on Wireless Communications and Networking (WCNC 2018), Barcelona, Spain
An Online Approach to D2D Trajectory Utility Maximization Problem
IEEE International Conference on Computer Communications (INFOCOM 2018), Honolulu, HI
Beyond Consensus and Synchrony in Decentralized Online Optimization using Saddle Point Method
51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CABest Student Paper Finalist
Asynchronous Resource Allocation in Distributed Heterogeneous Networks
IEEE International Conference on Communications (ICC 2017), Paris, France
Optimal Utilization of Storage Systems under Real-time Pricing
IEEE ICC Workshop on Smart Grid, Paris, France
BER-Optimized Robust Precoder Design for MIMO-OFDM Systems with Insufficient CP
IEEE Global Communications Conference (Globecom 2016), Washington DC
Online Load Scheduling Under Price and Demand Uncertainty in Smart Grid
International Conference on Signal Processing and Communications (SPCOM 2016), Bangalore, India