Search Results for author:
Found 70 papers, 34 papers with code
Universal Functional Regression with Neural Operator Flows
We empirically study the performance of OpFlow on regression and generation tasks with data generated from Gaussian processes with known posterior forms and non-Gaussian processes, as well as real-world earthquake seismograms with an unknown closed-form distribution.
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
On complex downstream tasks with limited data, such as fluid flow simulations and fluid-structure interactions, we found CoDA-NO to outperform existing methods on the few-shot learning task by over $36\%$.
Neural Operators with Localized Integral and Differential Kernels
In this work, we present a principled approach to operator learning that can capture local features under two frameworks by learning differential operators and integral operators with locally supported kernels.
Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction
Operator learning has been increasingly adopted in scientific and engineering applications, many of which require calibrated uncertainty quantification.
Equivariant Graph Neural Operator for Modeling 3D Dynamics
Modeling the complex three-dimensional (3D) dynamics of relational systems is an important problem in the natural sciences, with applications ranging from molecular simulations to particle mechanics.
Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs
Our contributions are threefold: i) we enable parallelization over input samples with a novel multi-grid-based domain decomposition, ii) we represent the parameters of the model in a high-order latent subspace of the Fourier domain, through a global tensor factorization, resulting in an extreme reduction in the number of parameters and improved generalization, and iii) we propose architectural improvements to the backbone FNO.
Neural Operators for Accelerating Scientific Simulations and Design
Scientific discovery and engineering design are currently limited by the time and cost of physical experiments, selected mostly through trial-and-error and intuition that require deep domain expertise.
Broadband Ground Motion Synthesis via Generative Adversarial Neural Operators: Development and Validation
Lastly, cGM-GANO produces similar median scaling to traditional GMMs for frequencies greater than 1Hz for both PSA and EAS but underestimates the aleatory variability of EAS.
Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces
Tipping points are abrupt, drastic, and often irreversible changes in the evolution of non-stationary and chaotic dynamical systems.
Speeding up Fourier Neural Operators via Mixed Precision
In this work, we (i) profile memory and runtime for FNO with full and mixed-precision training, (ii) conduct a study on the numerical stability of mixed-precision training of FNO, and (iii) devise a training routine which substantially decreases training time and memory usage (up to 34%), with little or no reduction in accuracy, on the Navier-Stokes and Darcy flow equations.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings.
Score-based Diffusion Models in Function Space
They consist of a forward process that perturbs input data with Gaussian white noise and a reverse process that learns a score function to generate samples by denoising.
PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators
In contrast to the concurrent works, which mainly focus on generating the motion of a single actor from the textual description, we generate the motion of one of the actors from the motion of the other participating actor in the action.
Fast Sampling of Diffusion Models via Operator Learning
Diffusion models have found widespread adoption in various areas.
Real-time high-resolution CO$_2$ geological storage prediction using nested Fourier neural operators
Carbon capture and storage (CCS) plays an essential role in global decarbonization.
Off-Policy Risk Assessment in Markov Decision Processes
To mitigate these problems, we incorporate model-based estimation to develop the first doubly robust (DR) estimator for the CDF of returns in MDPs.
Compactly Restrictable Metric Policy Optimization Problems
We study policy optimization problems for deterministic Markov decision processes (MDPs) with metric state and action spaces, which we refer to as Metric Policy Optimization Problems (MPOPs).
Supervised Learning with General Risk Functionals
Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class.
Langevin Monte Carlo for Contextual Bandits
Existing Thompson sampling-based algorithms need to construct a Laplace approximation (i. e., a Gaussian distribution) of the posterior distribution, which is inefficient to sample in high dimensional applications for general covariance matrices.
Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Regret in Linear Quadratic Control
By carefully prescribing an early exploration strategy and a policy update rule, we show that TS achieves order-optimal regret in adaptive control of multidimensional stabilizable LQRs.
KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems
However, current reinforcement learning (RL) methods lack stabilization guarantees, which limits their applicability for the control of safety-critical systems.
Functional Linear Regression of Cumulative Distribution Functions
In particular, given $n$ samples with $d$ basis functions, we show estimation error upper bounds of $\widetilde O(\sqrt{d/n})$ for fixed design, random design, and adversarial context cases.
Competitive Gradient Optimization
We provide a rate of convergence to stationary points and further propose a generalized class of $\alpha$-coherent function for which we provide convergence analysis.
Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.
Generative Adversarial Neural Operators
The inputs to the generator are samples of functions from a user-specified probability measure, e. g., Gaussian random field (GRF), and the generator outputs are synthetic data functions.
U-NO: U-shaped Neural Operators
We show that U-NO results in an average of 26% and 44% prediction improvement on Darcy's flow and turbulent Navier-Stokes equations, respectively, over the state of the art.
FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor.
Physics-Informed Neural Operator for Learning Partial Differential Equations
Specifically, in PINO, we combine coarse-resolution training data with PDE constraints imposed at a higher resolution.
U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow
Here we present U-FNO, a novel neural network architecture for solving multiphase flow problems with superior accuracy, speed, and data efficiency.
Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems
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
The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets.
Seismic wave propagation and inversion with Neural Operators
We develop a scheme to train Neural Operators on an ensemble of simulations performed with random velocity models and source locations.
Learning Dissipative Dynamics in Chaotic Systems
Chaotic systems are notoriously challenging to predict because of their sensitivity to perturbations and errors due to time stepping.
Meta-Adaptive Nonlinear Control: Theory and Algorithms
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.
Joint Stabilization and Regret Minimization through Switching in Over-Actuated Systems (extended version)
Adaptively controlling and minimizing regret in unknown dynamical systems while controlling the growth of the system state is crucial in real-world applications.
Off-Policy Risk Assessment in Contextual Bandits
Even when unable to run experiments, practitioners can evaluate prospective policies, using previously logged data.
On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk
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
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.
HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks
We introduce a scheme for probabilistic hypocenter inversion with Stein variational inference.
Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift
We deploy these estimators and provide generalization bounds in the unlabeled target domain.
Fourier Neural Operator for Parametric Partial Differential Equations
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces.
Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems.
Model-based Reinforcement Learning
reinforcement-learning
+1
Deep Bayesian Quadrature Policy Optimization
On the other hand, more sample efficient alternatives like Bayesian quadrature methods have received little attention due to their high computational complexity.
Competitive Policy Optimization
A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties.
Multipole Graph Neural Operator for Parametric Partial Differential Equations
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
We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs.
EikoNet: Solving the Eikonal equation with Deep Neural Networks
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
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
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
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
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
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
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).
Regularized Learning for Domain Adaptation under Label Shifts
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.
Stochastic Linear Bandits with Hidden Low Rank Structure
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.
Neural Lander: Stable Drone Landing Control using Learned Dynamics
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
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.
signSGD with Majority Vote is Communication Efficient And Fault Tolerant
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
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.
Stochastic Activation Pruning for Robust Adversarial Defense
Neural networks are known to be vulnerable to adversarial examples.
signSGD: Compressed Optimisation for Non-Convex Problems
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
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.
Avoiding Catastrophic States with Intrinsic Fear
Many practical reinforcement learning problems contain catastrophic states that the optimal policy visits infrequently or never.
Convergence rate of sign stochastic gradient descent for non-convex functions
The sign stochastic gradient descent method (signSGD) utilizes only the sign of the stochastic gradient in its updates.
Experimental results : Reinforcement Learning of POMDPs using Spectral Methods
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods.
Reinforcement Learning in Rich-Observation MDPs using Spectral Methods
We derive finite-time regret bounds for our algorithm with a weak dependence on the dimensionality of the observed space.
Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
We introduce intrinsic fear (IF), a learned reward shaping that guards DRL agents against periodic catastrophes.
Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies
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.
Reinforcement Learning of POMDPs using Spectral Methods
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods.
