no code implementations • 10 Apr 2024 • Anant A. Joshi, Amirhossein Taghvaei, Prashant G. Mehta, Sean P. Meyn
In this paper, stochastic optimal control problems in continuous time and space are considered.
no code implementations • 4 Mar 2024 • Amirhossein Taghvaei
The condition involves a coupled system of forward and backward stochastic differential equations (FBSDE) for the state and the adjoint processes.
1 code implementation • 9 Nov 2023 • Bamdad Hosseini, Alexander W. Hsu, Amirhossein Taghvaei
We present a systematic study of conditional triangular transport maps in function spaces from the perspective of optimal transportation and with a view towards amortized Bayesian inference.
no code implementations • 21 Oct 2023 • Mohammad Al-jarrah, Niyizhen Jin, Bamdad Hosseini, Amirhossein Taghvaei
This paper is concerned with the problem of nonlinear filtering, i. e., computing the conditional distribution of the state of a stochastic dynamical system given a history of noisy partial observations.
no code implementations • 17 Mar 2023 • Olga Movilla Miangolarra, Amirhossein Taghvaei, Tryphon T. Georgiou
Gradients in temperature and particle concentration fuel many processes in the physical and biological world.
no code implementations • 3 Jan 2023 • Amirhossein Taghvaei, Prashant G. Mehta
In this survey, we describe controlled interacting particle systems (CIPS) to approximate the solution of the optimal filtering and the optimal control problems.
no code implementations • 26 Oct 2022 • Shahriar Talebi, Amirhossein Taghvaei, Mehran Mesbahi
Specifically, building on the duality between synthesizing optimal control and estimation gains, the filter design problem is formalized as direct policy learning.
no code implementations • 23 Mar 2022 • Olga Movilla Miangolarra, Amirhossein Taghvaei, Yongxin Chen, Tryphon T. Georgiou
In contrast to the classical concept of a Carnot engine that alternates contact between heat baths of different temperatures, naturally occurring processes usually harvest energy from anisotropy, being exposed simultaneously to chemical and thermal fluctuations of different intensities.
no code implementations • 22 Mar 2022 • Amirhossein Taghvaei, Bamdad Hosseini
This paper presents a variational representation of the Bayes' law using optimal transportation theory.
1 code implementation • 4 Dec 2021 • Jiaojiao Fan, Qinsheng Zhang, Amirhossein Taghvaei, Yongxin Chen
Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions.
no code implementations • 2 Jul 2021 • Anant Joshi, Amirhossein Taghvaei, Prashant G. Mehta, Sean P. Meyn
This paper is concerned with optimal control problems for control systems in continuous time, and interacting particle system methods designed to construct approximate control solutions.
no code implementations • 2 Oct 2020 • S. Yagiz Olmez, Amirhossein Taghvaei, Prashant G. Mehta
The exact gain function is the solution of a Poisson equation involving a probability-weighted Laplacian.
2 code implementations • 8 Jul 2020 • Jiaojiao Fan, Amirhossein Taghvaei, Yongxin Chen
Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport.
no code implementations • 5 Oct 2019 • Amirhossein Taghvaei, Prashant G. Mehta
For this algorithm, the equations for empirical mean and covariance are derived and shown to be identical to the Kalman filter.
2 code implementations • ICML 2020 • Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
Building upon recent advances in the field of input convex neural networks, we propose a new framework where the gradient of one convex function represents the optimal transport mapping.
1 code implementation • 19 Feb 2019 • Amirhossein Taghvaei, Amin Jalali
We provide a framework to approximate the 2-Wasserstein distance and the optimal transport map, amenable to efficient training as well as statistical and geometric analysis.
no code implementations • 10 Jan 2019 • Amirhossein Taghvaei, Prashant G. Mehta
al. 2016) from vector valued variables to probability distributions.
no code implementations • 27 Sep 2018 • Amirhossein Taghvaei, Prashant G. Mehta
In particular, we extend the recent variational formulation of accelerated gradient methods in wibisono2016 from vector valued variables to probability distributions.
no code implementations • NeurIPS 2017 • Amirhossein Taghvaei, Jin W. Kim, Prashant G. Mehta
The formulation is used to provide a complete characterization of the critical points in terms of the solutions of a nonlinear matrix-valued equation, referred to as the characteristic equation.
no code implementations • 20 May 2016 • Daniel Khashabi, Kent Quanrud, Amirhossein Taghvaei
We consider the problem of strongly-convex online optimization in presence of adversarial delays; in a T-iteration online game, the feedback of the player's query at time t is arbitrarily delayed by an adversary for d_t rounds and delivered before the game ends, at iteration t+d_t-1.