Search Results for author: Shankar Sastry

Found 12 papers, 0 papers with code

Towards Dynamic Causal Discovery with Rare Events: A Nonparametric Conditional Independence Test

no code implementations29 Nov 2022 Chih-Yuan Chiu, Kshitij Kulkarni, Shankar Sastry

Causal phenomena associated with rare events occur across a wide range of engineering problems, such as risk-sensitive safety analysis, accident analysis and prevention, and extreme value theory.

Causal Discovery

Competing Bandits in Time Varying Matching Markets

no code implementations21 Oct 2022 Deepan Muthirayan, Chinmay Maheshwari, Pramod P. Khargonekar, Shankar Sastry

We study the problem of online learning in two-sided non-stationary matching markets, where the objective is to converge to a stable match.

Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets

no code implementations6 Jun 2022 Chinmay Maheshwari, Eric Mazumdar, Shankar Sastry

We study the problem of online learning in competitive settings in the context of two-sided matching markets.

Independent and Decentralized Learning in Markov Potential Games

no code implementations29 May 2022 Chinmay Maheshwari, Manxi Wu, Druv Pai, Shankar Sastry

In each stage of our learning dynamics, players update their estimate of a perturbed Q-function that evaluates their total contingent payoff based on the realized one-stage reward in an asynchronous manner.

Multi-agent Reinforcement Learning

Simultaneous Localization and Mapping: Through the Lens of Nonlinear Optimization

no code implementations11 Dec 2021 Amay Saxena, Chih-Yuan Chiu, Joseph Menke, Ritika Shrivastava, Shankar Sastry

This work presents an optimization-based framework that unifies these approaches, and allows users to flexibly implement different design choices, e. g., the number and types of variables maintained in the algorithm at each time.

Simultaneous Localization and Mapping

Dynamic Tolling for Inducing Socially Optimal Traffic Loads

no code implementations17 Oct 2021 Chinmay Maheshwari, Kshitij Kulkarni, Manxi Wu, Shankar Sastry

How to design tolls that induce socially optimal traffic loads with dynamically arriving travelers who make selfish routing decisions?

Residual Networks: Lyapunov Stability and Convex Decomposition

no code implementations22 Mar 2018 Kamil Nar, Shankar Sastry

While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception.

Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning

no code implementations6 Mar 2017 Joshua Achiam, Shankar Sastry

Exploration in complex domains is a key challenge in reinforcement learning, especially for tasks with very sparse rewards.

Continuous Control reinforcement-learning +1

Approximate Subspace-Sparse Recovery with Corrupted Data via Constrained $\ell_1$-Minimization

no code implementations23 Dec 2014 Ehsan Elhamifar, Mahdi Soltanolkotabi, Shankar Sastry

High-dimensional data often lie in low-dimensional subspaces corresponding to different classes they belong to.

CPRL -- An Extension of Compressive Sensing to the Phase Retrieval Problem

no code implementations NeurIPS 2012 Henrik Ohlsson, Allen Yang, Roy Dong, Shankar Sastry

This paper presents a novel extension of CS to the phase retrieval problem, where intensity measurements of a linear system are used to recover a complex sparse signal.

Compressive Sensing Retrieval

Markov Chain Monte Carlo Data Association for Multiple-Target Tracking

no code implementations IEEE Transactions on Automatic Control 2009 Songhwai Oh, Stuart Russell, Shankar Sastry

This paper presents Markov chain Monte Carlo data association (MCMCDA) for solving data association problems arising in multiple-target tracking in a cluttered environment.


Geometric Models of Rolling-Shutter Cameras

no code implementations29 Mar 2005 Marci Meingast, Christopher Geyer, Shankar Sastry

We develop a general projection equation for a rolling shutter camera and show how it is affected by different types of camera motion.

Cannot find the paper you are looking for? You can Submit a new open access paper.