170 citations · 539 across the 65 of their papers we have counts for
72 papers
Learning in Inverse Games: Tractable Training with Probabilistic Guarantees
Arghya Mallick, Reza Rahimi Baghbadorani, Peyman Mohajerin Esfahani +1
Inverse game theory seeks to learn agents' unknown objectives from observed equilibrium behavior. Existing residual-based approaches can lead to non-convex problems and need not en…
Limiting-Kernel Q(): Bridging Short and Long Horizons
Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani +1
In reinforcement learning, more accurate policy evaluation has been frequently shown to improve downstream policy optimization performance. For tractability, most value estimators…
Benign Geometry and Distributional Robustness of Synthesis
Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Tamás Keviczky +1
In this paper, we study standard and distributionally robust synthesis problem of a stabilizing state-feedback controller for discrete-time linear time-invariant sy…
Adaptive Incentive Design in Dynamic Principal-Agent Problem via Kernelized Bandits
Arghya Mallick, Anuj S. Vora, Sergio Grammatico +1
We consider the dynamic principal-agent problem under asymmetric information, wherein a principal sequentially designs contracts to incentivize an agent with unknown preferences an…
Discrete-Time Adaptive Control in High Dimensions: Near Dimension-Free Performance via Mirror Descent
Mohammad Boveiri, Peyman Mohajerin Esfahani
Motivated by the use of modern high-capacity models in real-time control problems, this paper studies the adaptive control of high-dimensional discrete-time nonlinear systems with…
Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
Sasan Vakili, Daniël Woonings, Pradyumna Paruchuri +1
This paper presents a nonlinear parameter estimator for Wiener-type state-space models obtained as a fixed-point architecture that couples two affine minimum mean-squared error (MM…
Tight Generalization Bounds for Noiseless Inverse Optimization
Pouria Fatemi, Hoomaan Maskan, Suvrit Sra +1
Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed context--action data. We study noiseless IO, where demonstrations are generate…
A Hybrid Algorithm for Monotone Variational Inequalities
Reza Rahimi Baghbadorani, Peyman Mohajerin Esfahani, Sergio Grammatico
Inspired by the adaptive Golden Ratio Algorithm (aGRAAL), we propose two new methods for solving monotone variational inequalities. We show that by selecting the momentum parameter…
Rate or Fate? RLVR: Reinforcement Learning with Verifiable Noisy Rewards
Ali Rad, Khashayar Filom, Darioush Keivan +2
Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the ver…
Control and Reinforcement Learning through the Lens of Optimization: An Algorithmic Perspective
Tolga Ok, Arman Sharifi Kolarijani, Mohamad Amin Sharif Kolarijani +1
The connection between control algorithms for Markov decision processes and optimization algorithms has been implicitly and explicitly exploited since the introduction of dynamic p…
Locally Linear Convergence for Nonsmooth Convex Optimization via Coupled Smoothing and Momentum
Reza Rahimi Baghbadorani, Sergio Grammatico, Peyman Mohajerin Esfahani
We propose an adaptive accelerated smoothing technique for a nonsmooth convex optimization problem where the smoothing update rule is coupled with the momentum parameter. We also e…
Accelerating Adaptive Systems via Normalized Parameter Estimation Laws
Mohammad Boveiri, Mohammad Khosravi, Peyman Mohajerin Esfahani
In this paper, we propose a new class of parameter estimation laws for adaptive systems, called \emph{normalized parameter estimation laws}. A key feature of these estimation laws…
A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities
Reza Rahimi Baghbadorani, Peyman Mohajerin Esfahani, Sergio Grammatico
We propose an accelerated algorithm with a Frank-Wolfe method as an oracle for solving strongly monotone variational inequality problems. While standard solution approaches, such a…
Data-Driven Fault Isolation in Linear Time-Invariant Systems: A Subspace Classification Approach
Mohammad Amin Sheikhi, Gabriel de Albuquerque Gleizer, Peyman Mohajerin Esfahani +1
We study the problem of fault isolation in linear systems with actuator and sensor faults within a data-driven framework. We propose a nullspace-based filter that uses solely fault…
Active Estimation of Multiplicative Faults in Dynamical Systems
Gabriel de Albuquerque Gleizer, Peyman Mohajerin Esfahani, Tamas Keviczky
This paper addresses the problem of estimating multiplicative fault signals in linear time-invariant systems by processing its input and output variables, as well as designing an i…
Efficient Uncertainty Propagation with Guarantees in Wasserstein Distance
Eduardo Figueiredo, Steven Adams, Peyman Mohajerin Esfahani +1
In this paper, we consider the problem of propagating an uncertain distribution by a possibly non-linear function and quantifying the resulting uncertainty. We measure the uncertai…
A Saddle Point Algorithm for Robust Data-Driven Factor Model Problems
Shabnam Khodakaramzadeh, Soroosh Shafiee, Gabriel de Albuquerque Gleizer +1
We study the factor model problem, which aims to uncover low-dimensional structures in high-dimensional datasets. Adopting a robust data-driven approach, we formulate the problem a…
Inverse Optimization via Learning Feasible Regions
Ke Ren, Peyman Mohajerin Esfahani, Angelos Georghiou
We study inverse optimization (IO), where the goal is to use a parametric optimization program as the hypothesis class to infer relationships between input-decision pairs. Most of…
User-centric Vehicle-to-Grid Optimization with an Input Convex Neural Network-based Battery Degradation Model
Arghya Mallick, Georgios Pantazis, Mohammad Khosravi +2
We propose a data-driven, user-centric vehicle-to-grid (V2G) methodology based on multi-objective optimization to balance battery degradation and V2G revenue according to EV user p…
A User-centric Game for Balancing V2G Benefits with Battery Degradation of Electric Vehicles
Arghya Mallick, Georgios Pantazis, Peyman Mohajerin Esfahani +1
We present a novel user-centric vehicle-to-grid (V2G) framework that enables electric vehicle (EV) users to balance the trade-off between financial benefits from V2G and battery he…
Rank-One Modified Value Iteration
Arman Sharifi Kolarijani, Tolga Ok, Peyman Mohajerin Esfahani +1
In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update b…
Optimal Bayesian Affine Estimator and Active Learning for the Wiener Model
Sasan Vakili, Manuel Mazo, Peyman Mohajerin Esfahani
This paper presents a Bayesian estimation framework for Wiener models, focusing on learning nonlinear output functions under known linear state dynamics. We derive a closed-form op…
Offline Reinforcement Learning via Inverse Optimization
Ioannis Dimanidis, Tolga Ok, Peyman Mohajerin Esfahani
Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous s…
Scalable Kernel Inverse Optimization
Youyuan Long, Tolga Ok, Pedro Zattoni Scroccaro +1
Inverse Optimization (IO) is a framework for learning the unknown objective function of an expert decision-maker from a past dataset. In this paper, we extend the hypothesis class…