Search Results for author: George J. Pappas

Found 57 papers, 21 papers with code

NOMAD: Nonlinear Manifold Decoders for Operator Learning

no code implementations7 Jun 2022 Jacob H. Seidman, Georgios Kissas, Paris Perdikaris, George J. Pappas

Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling.

Operator learning

Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds

no code implementations6 Jun 2022 Aritra Mitra, Arman Adibi, George J. Pappas, Hamed Hassani

We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret.

Risk of Stochastic Systems for Temporal Logic Specifications

no code implementations28 May 2022 Lars Lindemann, Lejun Jiang, Nikolai Matni, George J. Pappas

For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly.

Autonomous Driving

Learning to Control Linear Systems can be Hard

no code implementations27 May 2022 Anastasios Tsiamis, Ingvar Ziemann, Manfred Morari, Nikolai Matni, George J. Pappas

In this paper, we study the statistical difficulty of learning to control linear systems.

online learning

Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents

no code implementations7 Apr 2022 Arman Adibi, Aritra Mitra, George J. Pappas, Hamed Hassani

Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control and optimization, and reinforcement learning.

Adaptive Stochastic MPC under Unknown Noise Distribution

no code implementations3 Apr 2022 Charis Stamouli, Anastasios Tsiamis, Manfred Morari, George J. Pappas

Then, we employ this benchmark controller to derive a novel robustly stable adaptive SMPC scheme that learns the necessary noise statistics online, while guaranteeing time-uniform satisfaction of the unknown reformulated state constraints with high probability.

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks

1 code implementation2 Apr 2022 Anton Xue, Lars Lindemann, Alexander Robey, Hamed Hassani, George J. Pappas, Rajeev Alur

Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data.

Image Classification

Temporal Robustness of Temporal Logic Specifications: Analysis and Control Design

no code implementations29 Mar 2022 Alëna Rodionova, Lars Lindemann, Manfred Morari, George J. Pappas

We study the temporal robustness of temporal logic specifications and show how to design temporally robust control laws for time-critical control systems.

Do Deep Networks Transfer Invariances Across Classes?

1 code implementation ICLR 2022 Allan Zhou, Fahim Tajwar, Alexander Robey, Tom Knowles, George J. Pappas, Hamed Hassani, Chelsea Finn

Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.

Image Classification

Linear Stochastic Bandits over a Bit-Constrained Channel

no code implementations2 Mar 2022 Aritra Mitra, Hamed Hassani, George J. Pappas

Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity.

Decision Making Decision Making Under Uncertainty

Temporal Robustness of Stochastic Signals

1 code implementation5 Feb 2022 Lars Lindemann, Alena Rodionova, George J. Pappas

We then define the temporal robustness risk by investigating the temporal robustness of the realizations of a stochastic signal.

Autonomous Driving

Probabilistically Robust Learning: Balancing Average- and Worst-case Performance

1 code implementation2 Feb 2022 Alexander Robey, Luiz F. O. Chamon, George J. Pappas, Hamed Hassani

From a theoretical point of view, this framework overcomes the trade-offs between the performance and the sample-complexity of worst-case and average-case learning.

Learning Operators with Coupled Attention

no code implementations4 Jan 2022 Georgios Kissas, Jacob Seidman, Leonardo Ferreira Guilhoto, Victor M. Preciado, George J. Pappas, Paris Perdikaris

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data.

Operator learning

Learning Rigidity-based Flocking Control with Gaussian Processes

no code implementations14 Dec 2021 Manuela Gamonal, Thomas Beckers, George J. Pappas, Leonardo J. Colombo

We provide a decentralized control law that exponentially stabilizes the motion of the agents and captures Reynolds boids motion for swarms by using GPs as an online learning-based oracle for the prediction of the unknown dynamics.

Gaussian Processes online learning

Adversarial Robustness with Semi-Infinite Constrained Learning

no code implementations NeurIPS 2021 Alexander Robey, Luiz F. O. Chamon, George J. Pappas, Hamed Hassani, Alejandro Ribeiro

In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely.

Adversarial Robustness

Learning Region of Attraction for Nonlinear Systems

no code implementations2 Oct 2021 Shaoru Chen, Mahyar Fazlyab, Manfred Morari, George J. Pappas, Victor M. Preciado

Estimating the region of attraction (ROA) of general nonlinear autonomous systems remains a challenging problem and requires a case-by-case analysis.

Reactive and Risk-Aware Control for Signal Temporal Logic

no code implementations30 Aug 2021 Lars Lindemann, George J. Pappas, Dimos V. Dimarogonas

Addressing these is pivotal to build fully autonomous systems and requires a systematic integration of planning and control.

Safe Pontryagin Differentiable Programming

1 code implementation NeurIPS 2021 Wanxin Jin, Shaoshuai Mou, George J. Pappas

We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic framework to solve a broad class of safety-critical learning and control tasks -- problems that require the guarantee of safety constraint satisfaction at any stage of the learning and control progress.

Motion Planning

Time-Robust Control for STL Specifications

1 code implementation6 Apr 2021 Alena Rodionova, Lars Lindemann, Manfred Morari, George J. Pappas

We present a robust control framework for time-critical systems in which satisfying real-time constraints robustly is of utmost importance for the safety of the system.

STL Robustness Risk over Discrete-Time Stochastic Processes

no code implementations3 Apr 2021 Lars Lindemann, Nikolai Matni, George J. Pappas

We then define the risk of a stochastic process not satisfying an STL formula robustly, referred to as the STL robustness risk.

Linear Systems can be Hard to Learn

no code implementations2 Apr 2021 Anastasios Tsiamis, George J. Pappas

Statistically easy to learn linear system classes have sample complexity that is polynomial with the system dimension.

Model-Based Domain Generalization

1 code implementation NeurIPS 2021 Alexander Robey, George J. Pappas, Hamed Hassani

Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data.

Domain Generalization

Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients

no code implementations NeurIPS 2021 Aritra Mitra, Rayana Jaafar, George J. Pappas, Hamed Hassani

We consider a standard federated learning (FL) architecture where a group of clients periodically coordinate with a central server to train a statistical model.

Federated Learning

Is the brain macroscopically linear? A system identification of resting state dynamics

1 code implementation22 Dec 2020 Erfan Nozari, Maxwell A. Bertolero, Jennifer Stiso, Lorenzo Caciagli, Eli J. Cornblath, Xiaosong He, Arun S. Mahadevan, George J. Pappas, Dani Smith Bassett

Contrary to our expectations, linear auto-regressive models achieve the best measures across all three metrics, eliminating the trade-off between accuracy and simplicity.

EEG

Learning Lyapunov Functions for Hybrid Systems

no code implementations22 Dec 2020 Shaoru Chen, Mahyar Fazlyab, Manfred Morari, George J. Pappas, Victor M. Preciado

By designing the learner and the verifier according to the analytic center cutting-plane method from convex optimization, we show that when the set of Lyapunov functions is full-dimensional in the parameter space, our method finds a Lyapunov function in a finite number of steps.

Optimization and Control

Scalable Reinforcement Learning Policies for Multi-Agent Control

1 code implementation16 Nov 2020 Christopher D. Hsu, Heejin Jeong, George J. Pappas, Pratik Chaudhari

Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets.

Multi-agent Reinforcement Learning reinforcement-learning

Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processes

no code implementations12 Oct 2020 Pushpak Jagtap, George J. Pappas, Majid Zamani

This paper focuses on the controller synthesis for unknown, nonlinear systems while ensuring safety constraints.

Gaussian Processes

Online learning-based trajectory tracking for underactuated vehicles with uncertain dynamics

no code implementations14 Sep 2020 Thomas Beckers, Leonardo Colombo, Sandra Hirche, George J. Pappas

To overcome this issue, we present a tracking control law for underactuated rigid-body dynamics using an online learning-based oracle for the prediction of the unknown dynamics.

online learning

Learning to Track Dynamic Targets in Partially Known Environments

1 code implementation17 Jun 2020 Heejin Jeong, Hamed Hassani, Manfred Morari, Daniel D. Lee, George J. Pappas

In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration.

Zeroth-order Deterministic Policy Gradient

no code implementations12 Jun 2020 Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas, Alejandro Ribeiro

Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes.

Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data

1 code implementation20 May 2020 Alexander Robey, Hamed Hassani, George J. Pappas

Indeed, natural variation such as lighting or weather conditions can significantly degrade the accuracy of trained neural networks, proving that such natural variation presents a significant challenge for deep learning.

Adversarial Robustness

Teaching Recurrent Neural Networks to Modify Chaotic Memories by Example

no code implementations3 May 2020 Jason Z. Kim, Zhixin Lu, Erfan Nozari, George J. Pappas, Danielle S. Bassett

Here we demonstrate that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and we explain the associated learning mechanism with new theory.

Time Series

Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees

no code implementations L4DC 2020 Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado, George J. Pappas

By interpreting the min-max problem as an optimal control problem, it has recently been shown that one can exploit the compositional structure of neural networks in the optimization problem to improve the training time significantly.

Robust classification

Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programming

no code implementations16 Apr 2020 Haimin Hu, Mahyar Fazlyab, Manfred Morari, George J. Pappas

There has been an increasing interest in using neural networks in closed-loop control systems to improve performance and reduce computational costs for on-line implementation.

Sample Complexity of Kalman Filtering for Unknown Systems

no code implementations L4DC 2020 Anastasios Tsiamis, Nikolai Matni, George J. Pappas

We show that when the system identification step produces sufficiently accurate estimates, or when the underlying true KF is sufficiently robust, that a Certainty Equivalent (CE) KF, i. e., one designed using the estimated parameters directly, enjoys provable sub-optimality guarantees.

Risk-Aware MMSE Estimation

no code implementations6 Dec 2019 Dionysios S. Kalogerias, Luiz. F. O. Chamon, George J. Pappas, Alejandro Ribeiro

Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable.

Model-Free Learning of Optimal Ergodic Policies in Wireless Systems

no code implementations10 Nov 2019 Dionysios S. Kalogerias, Mark Eisen, George J. Pappas, Alejandro Ribeiro

Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates.

Statistical Learning for Analysis of Networked Control Systems over Unknown Channels

no code implementations8 Nov 2019 Konstantinos Gatsis, George J. Pappas

In this regard our work is the first to characterize the amount of channel modeling that is required to answer such a question.

Learning Q-network for Active Information Acquisition

2 code implementations23 Oct 2019 Heejin Jeong, Brent Schlotfeldt, Hamed Hassani, Manfred Morari, Daniel D. Lee, George J. Pappas

In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors.

reinforcement-learning

Probabilistic Verification and Reachability Analysis of Neural Networks via Semidefinite Programming

1 code implementation9 Oct 2019 Mahyar Fazlyab, Manfred Morari, George J. Pappas

In this context, we discuss two relevant problems: (i) probabilistic safety verification, in which the goal is to find an upper bound on the probability of violating a safety specification; and (ii) confidence ellipsoid estimation, in which given a confidence ellipsoid for the input of the neural network, our goal is to compute a confidence ellipsoid for the output.

Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning

no code implementations2 Oct 2019 Lifeng Zhou, Vasileios Tzoumas, George J. Pappas, Pratap Tokekar

Since, DRM overestimates the number of attacks in each clique, in this paper we also introduce an Improved Distributed Robust Maximization (IDRM) algorithm.

Motion Planning

Optimal Algorithms for Submodular Maximization with Distributed Constraints

no code implementations30 Sep 2019 Alexander Robey, Arman Adibi, Brent Schlotfeldt, George J. Pappas, Hamed Hassani

Given this distributed setting, we develop Constraint-Distributed Continuous Greedy (CDCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication.

Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees

1 code implementation11 Sep 2019 Mohammadhosein Hasanbeig, Yiannis Kantaros, Alessandro Abate, Daniel Kroening, George J. Pappas, Insup Lee

Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology.

Decision Making Decision Making Under Uncertainty +3

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

1 code implementation NeurIPS 2019 Mahyar Fazlyab, Alexander Robey, Hamed Hassani, Manfred Morari, George J. Pappas

The resulting SDP can be adapted to increase either the estimation accuracy (by capturing the interaction between activation functions of different layers) or scalability (by decomposition and parallel implementation).

Finite Sample Analysis of Stochastic System Identification

no code implementations21 Mar 2019 Anastasios Tsiamis, George J. Pappas

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics.

Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming

4 code implementations4 Mar 2019 Mahyar Fazlyab, Manfred Morari, George J. Pappas

Certifying the safety or robustness of neural networks against input uncertainties and adversarial attacks is an emerging challenge in the area of safe machine learning and control.

Network Design for Controllability Metrics

1 code implementation12 Feb 2019 Cassiano O. Becker, Sérgio Pequito, George J. Pappas, Victor M. Preciado

In this setting, we first consider a feasibility problem consisting of tuning the edge weights such that certain controllability properties are satisfied.

Optimization and Control

Verisig: verifying safety properties of hybrid systems with neural network controllers

1 code implementation5 Nov 2018 Radoslav Ivanov, James Weimer, Rajeev Alur, George J. Pappas, Insup Lee

This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers.

Systems and Control

Cloud-based Quadratic Optimization with Partially Homomorphic Encryption

1 code implementation7 Sep 2018 Andreea B. Alexandru, Konstantinos Gatsis, Yasser Shoukry, Sanjit A. Seshia, Paulo Tabuada, George J. Pappas

The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.

Optimization and Control Cryptography and Security Systems and Control

Resilient Non-Submodular Maximization over Matroid Constraints

no code implementations2 Apr 2018 Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas

The objective of this paper is to focus on resilient matroid-constrained problems arising in control and sensing but in the presence of sensor and actuator failures.

Robot Navigation

Cloud-based MPC with Encrypted Data

1 code implementation27 Mar 2018 Andreea B. Alexandru, Manfred Morari, George J. Pappas

We propose protocols for two cloud-MPC architectures motivated by the current developments in the Internet of Things: a client-server architecture and a two-server architecture.

Optimization and Control Cryptography and Security Systems and Control

Resilient Active Information Gathering with Mobile Robots

no code implementations26 Mar 2018 Brent Schlotfeldt, Vasileios Tzoumas, Dinesh Thakur, George J. Pappas

In this paper, we provide the first algorithm, enabling the following capabilities: minimal communication, i. e., the algorithm is executed by the robots based only on minimal communication between them; system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks and failures; and provable approximation performance, i. e., the algorithm ensures for all monotone (and not necessarily submodular) objective functions a solution that is finitely close to the optimal.

Resilient Monotone Sequential Maximization

no code implementations21 Mar 2018 Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas

In this paper, we provide the first scalable algorithm, that achieves the following characteristics: system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks, deletions, or failures; adaptiveness, i. e., at each time step, the algorithm selects system elements based on the history of inflicted attacks, deletions, or failures; and provable approximation performance, i. e., the algorithm guarantees for monotone objective functions a solution close to the optimal.

Robot Navigation

Dense 3-D Mapping with Spatial Correlation via Gaussian Filtering

no code implementations23 Jan 2018 Ke Sun, Kelsey Saulnier, Nikolay Atanasov, George J. Pappas, Vijay Kumar

Many accurate and efficient methods exist that address this problem but most assume that the occupancy states of different elements in the map representation are statistically independent.

Robotics

Assumed Density Filtering Q-learning

1 code implementation9 Dec 2017 Heejin Jeong, Clark Zhang, George J. Pappas, Daniel D. Lee

We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs.

Atari Games Bayesian Inference +1

Active Deformable Part Models

no code implementations1 Apr 2014 Menglong Zhu, Nikolay Atanasov, George J. Pappas, Kostas Daniilidis

This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction.

General Classification object-detection +1

Nonmyopic View Planning for Active Object Detection

no code implementations20 Sep 2013 Nikolay Atanasov, Bharath Sankaran, Jerome Le Ny, George J. Pappas, Kostas Daniilidis

One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose.

Active Object Detection object-detection +2

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