Search Results for author: Kamyar Azizzadenesheli

Found 42 papers, 16 papers with code

Physics-Informed Neural Operator for Learning Partial Differential Equations

1 code implementation6 Nov 2021 Zongyi Li, Hongkai Zheng, Nikola Kovachki, David Jin, Haoxuan Chen, Burigede Liu, Kamyar Azizzadenesheli, Anima Anandkumar

The Physics-Informed Neural Network (PINN) is an example of the former while the Fourier neural operator (FNO) is an example of the latter.

Operator learning

U-FNO -- an enhanced Fourier neural operator based-deep learning model for multiphase flow

no code implementations3 Sep 2021 Gege Wen, Zongyi Li, Kamyar Azizzadenesheli, Anima Anandkumar, Sally M. Benson

Data-driven machine learning methods provide faster alternatives to traditional simulators by training neural network models with numerical simulation data mappings.

Decision Making

Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems

no code implementations26 Aug 2021 Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

Using these guarantees, we design adaptive control algorithms for unknown ARX systems with arbitrary strongly convex or convex quadratic regulating costs.

Neural Operator: Learning Maps Between Function Spaces

no code implementations19 Aug 2021 Nikola Kovachki, Zongyi Li, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar

We propose a generalization of neural networks tailored to learn operators mapping between infinite dimensional function spaces.

Operator learning

Seismic wave propagation and inversion with Neural Operators

no code implementations11 Aug 2021 Yan Yang, Angela F. Gao, Jorge C. Castellanos, Zachary E. Ross, Kamyar Azizzadenesheli, Robert W. Clayton

We develop a scheme to train Neural Operators on an ensemble of simulations performed with random velocity models and source locations.

Markov Neural Operators for Learning Chaotic Systems

no code implementations13 Jun 2021 Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar

Experiments show neural operators are more accurate and stable compared to previous methods on chaotic systems such as the Kuramoto-Sivashinsky and Navier-Stokes equations.

Meta-Adaptive Nonlinear Control: Theory and Algorithms

1 code implementation NeurIPS 2021 Guanya Shi, Kamyar Azizzadenesheli, Michael O'Connell, Soon-Jo Chung, Yisong Yue

We provide instantiations of our approach under varying conditions, leading to the first non-asymptotic end-to-end convergence guarantee for multi-task nonlinear control.

Multi-Task Learning Representation Learning

Joint Stabilization and Regret Minimization through Switching in Systems with Actuator Redundancy

no code implementations31 May 2021 Jafar Abbaszadeh Chekan, Kamyar Azizzadenesheli, Cedric Langbort

We propose an optimism-based algorithm that utilizes the actuator redundancy and the possibility of switching between actuating modes to guarantee the boundedness of the state.

Off-Policy Risk Assessment in Contextual Bandits

no code implementations NeurIPS 2021 Audrey Huang, Liu Leqi, Zachary C. Lipton, Kamyar Azizzadenesheli

Even when unable to run experiments, practitioners can evaluate prospective policies, using previously logged data.

Multi-Armed Bandits

On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk

no code implementations4 Mar 2021 Audrey Huang, Liu Leqi, Zachary C. Lipton, Kamyar Azizzadenesheli

Because optimizing the coherent risk is difficult in Markov decision processes, recent work tends to focus on the Markov coherent risk (MCR), a time-consistent surrogate.

Multi-Agent Multi-Armed Bandits with Limited Communication

no code implementations10 Feb 2021 Mridul Agarwal, Vaneet Aggarwal, Kamyar Azizzadenesheli

With our algorithm, LCC-UCB, each agent enjoys a regret of $\tilde{O}\left(\sqrt{({K/N}+ N)T}\right)$, communicates for $O(\log T)$ steps and broadcasts $O(\log K)$ bits in each communication step.

Multi-Armed Bandits

Explore More and Improve Regret in Linear Quadratic Regulators

no code implementations23 Jul 2020 Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

In the absence of such a stabilizing controller, at the early stages, the lack of reasonable model estimates needed for (i) strategic exploration and (ii) design of controllers that stabilize the system, results in regret that scales exponentially in the problem dimensions.

Deep Bayesian Quadrature Policy Optimization

1 code implementation28 Jun 2020 Akella Ravi Tej, Kamyar Azizzadenesheli, Mohammad Ghavamzadeh, Anima Anandkumar, Yisong Yue

On the other hand, more sample efficient alternatives like Bayesian quadrature methods have received little attention due to their high computational complexity.

Continuous Control Policy Gradient Methods

Competitive Policy Optimization

2 code implementations18 Jun 2020 Manish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger, Yisong Yue, Anima Anandkumar

A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties.

Policy Gradient Methods

Multipole Graph Neural Operator for Parametric Partial Differential Equations

2 code implementations NeurIPS 2020 Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar

One of the main challenges in using deep learning-based methods for simulating physical systems and solving partial differential equations (PDEs) is formulating physics-based data in the desired structure for neural networks.

MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

1 code implementation1 May 2020 Chiyu Max Jiang, Soheil Esmaeilzadeh, Kamyar Azizzadenesheli, Karthik Kashinath, Mustafa Mustafa, Hamdi A. Tchelepi, Philip Marcus, Prabhat, Anima Anandkumar

We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs.

Super-Resolution

EikoNet: Solving the Eikonal equation with Deep Neural Networks

1 code implementation25 Mar 2020 Jonathan D. Smith, Kamyar Azizzadenesheli, Zachary E. Ross

Here, we propose EikoNet, a deep learning approach to solving the Eikonal equation, which characterizes the first-arrival-time field in heterogeneous 3D velocity structures.

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

no code implementations NeurIPS 2020 Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We study the problem of system identification and adaptive control in partially observable linear dynamical systems.

Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting

no code implementations12 Mar 2020 Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We study the problem of adaptive control in partially observable linear quadratic Gaussian control systems, where the model dynamics are unknown a priori.

Neural Operator: Graph Kernel Network for Partial Differential Equations

3 code implementations ICLR Workshop DeepDiffEq 2019 Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar

The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces.

Regret Minimization in Partially Observable Linear Quadratic Control

no code implementations31 Jan 2020 Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We propose a novel way to decompose the regret and provide an end-to-end sublinear regret upper bound for partially observable linear quadratic control.

Directivity Modes of Earthquake Populations with Unsupervised Learning

no code implementations30 Jun 2019 Zachary E. Ross, Daniel T. Trugman, Kamyar Azizzadenesheli, Anima Anandkumar

A seismic spectral decomposition technique is used to first produce relative measurements of radiated energy for earthquakes in a spatially-compact cluster.

Learning Causal State Representations of Partially Observable Environments

no code implementations25 Jun 2019 Amy Zhang, Zachary C. Lipton, Luis Pineda, Kamyar Azizzadenesheli, Anima Anandkumar, Laurent Itti, Joelle Pineau, Tommaso Furlanello

In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP).

Causal Inference

Regularized Learning for Domain Adaptation under Label Shifts

2 code implementations ICLR 2019 Kamyar Azizzadenesheli, Anqi Liu, Fanny Yang, Animashree Anandkumar

We derive a generalization bound for the classifier on the target domain which is independent of the (ambient) data dimensions, and instead only depends on the complexity of the function class.

Domain Adaptation

Stochastic Linear Bandits with Hidden Low Rank Structure

no code implementations28 Jan 2019 Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi

We modify the image classification task into the SLB setting and empirically show that, when a pre-trained DNN provides the high dimensional feature representations, deploying PSLB results in significant reduction of regret and faster convergence to an accurate model compared to state-of-art algorithm.

Decision Making Dimensionality Reduction +1

Neural Lander: Stable Drone Landing Control using Learned Dynamics

no code implementations19 Nov 2018 Guanya Shi, Xichen Shi, Michael O'Connell, Rose Yu, Kamyar Azizzadenesheli, Animashree Anandkumar, Yisong Yue, Soon-Jo Chung

To the best of our knowledge, this is the first DNN-based nonlinear feedback controller with stability guarantees that can utilize arbitrarily large neural nets.

Policy Gradient in Partially Observable Environments: Approximation and Convergence

no code implementations18 Oct 2018 Kamyar Azizzadenesheli, Yisong Yue, Animashree Anandkumar

Deploying these tools, we generalize a variety of existing theoretical guarantees, such as policy gradient and convergence theorems, to partially observable domains, those which also could be carried to more settings of interest.

Decision Making Policy Gradient Methods

signSGD with Majority Vote is Communication Efficient And Fault Tolerant

2 code implementations ICLR 2019 Jeremy Bernstein, Jia-Wei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar

Workers transmit only the sign of their gradient vector to a server, and the overall update is decided by a majority vote.

Surprising Negative Results for Generative Adversarial Tree Search

3 code implementations ICLR 2019 Kamyar Azizzadenesheli, Brandon Yang, Weitang Liu, Zachary C. Lipton, Animashree Anandkumar

We deploy this model and propose generative adversarial tree search (GATS) a deep RL algorithm that learns the environment model and implements Monte Carlo tree search (MCTS) on the learned model for planning.

Atari Games

signSGD: Compressed Optimisation for Non-Convex Problems

2 code implementations ICML 2018 Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar

Using a theorem by Gauss we prove that majority vote can achieve the same reduction in variance as full precision distributed SGD.

Efficient Exploration through Bayesian Deep Q-Networks

1 code implementation ICLR 2018 Kamyar Azizzadenesheli, Animashree Anandkumar

This allows us to directly incorporate the uncertainty over the Q-function and deploy Thompson sampling on the learned posterior distribution resulting in efficient exploration/exploitation trade-off.

Atari Games Efficient Exploration

Experimental results : Reinforcement Learning of POMDPs using Spectral Methods

no code implementations7 May 2017 Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods.

Latent Variable Models

Reinforcement Learning in Rich-Observation MDPs using Spectral Methods

no code implementations11 Nov 2016 Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar

We derive finite-time regret bounds for our algorithm with a weak dependence on the dimensionality of the observed space.

Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies

no code implementations17 Aug 2016 Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar

Generally in RL, one can assume a generative model, e. g. graphical models, for the environment, and then the task for the RL agent is to learn the model parameters and find the optimal strategy based on these learnt parameters.

Decision Making

Reinforcement Learning of POMDPs using Spectral Methods

no code implementations25 Feb 2016 Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods.

Latent Variable Models

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