1.1k citations · 7.8k across the 180 of their papers we have counts for
24 papers · 1 filter
Stability and Identification of Random Asynchronous Linear Time-Invariant Systems
Sahin Lale, Oguzhan Teke, Babak Hassibi +1
In many computational tasks and dynamical systems, asynchrony and randomization are naturally present and have been considered as ways to increase the speed and reduce the cost of…
Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces
Zhuoran Qiao, Feizhi Ding, Matthew Welborn +5
We refine the OrbNet model to accurately predict energy, forces, and other response properties for molecules using a graph neural-network architecture based on features from low-co…
MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models
Peng Xu, Mostofa Patwary, Mohammad Shoeybi +4
Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel fr…
Fourier Neural Operator for Parametric Partial Differential Equations
Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli +4
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural o…
Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach
Haoxuan Wang, Zhiding Yu, Yisong Yue +3
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect su…
Deep learning-based computer vision to recognize and classify suturing gestures in robot-assisted surgery
Francisco Luongo, Ryan Hakim, Jessica H. Nguyen +2
Our previous work classified a taxonomy of suturing gestures during a vesicourethral anastomosis of robotic radical prostatectomy in association with tissue tears and patient outco…
OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Hongyu Ren, Yuke Zhu, Jure Leskovec +2
Real-world tasks often exhibit a compositional structure that contains a sequence of simpler sub-tasks. For instance, opening a door requires reaching, grasping, rotating, and pull…
Automated Synthetic-to-Real Generalization
Wuyang Chen, Zhiding Yu, Zhangyang Wang +1
Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Ye…
Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknow…
Unsupervised Controllable Generation with Self-Training
Grigorios G Chrysos, Jean Kossaifi, Zhiding Yu +1
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research prob…
Neural Networks with Recurrent Generative Feedback
Yujia Huang, James Gornet, Sihui Dai +4
Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The B…
Competitive Policy Optimization
Manish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger +2
A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties…
Competitive Mirror Descent
Florian Schäfer, Anima Anandkumar, Houman Owhadi
Constrained competitive optimization involves multiple agents trying to minimize conflicting objectives, subject to constraints. This is a highly expressive modeling language that…
Deep Bayesian Quadrature Policy Optimization
Akella Ravi Tej, Kamyar Azizzadenesheli, Mohammad Ghavamzadeh +2
We study the problem of obtaining accurate policy gradient estimates using a finite number of samples. Monte-Carlo methods have been the default choice for policy gradient estimati…
Learning compositional functions via multiplicative weight updates
Jeremy Bernstein, Jiawei Zhao, Markus Meister +3
Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems l…
Multipole Graph Neural Operator for Parametric Partial Differential Equations
Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli +4
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…
Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
Yashwanth Kumar Nakka, Anqi Liu, Guanya Shi +3
Learning-based control algorithms require data collection with abundant supervision for training. Safe exploration algorithms ensure the safety of this data collection process even…
MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework
Chiyu Max Jiang, Soheil Esmaeilzadeh, Kamyar Azizzadenesheli +6
We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. Whil…
Spectral Learning on Matrices and Tensors
Majid Janzamin, Rong Ge, Jean Kossaifi +1
Spectral methods have been the mainstay in several domains such as machine learning and scientific computing. They involve finding a certain kind of spectral decomposition to obtai…
Regret Minimization in Partially Observable Linear Quadratic Control
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1
We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-…
Neural Operator: Graph Kernel Network for Partial Differential Equations
Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli +4
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 Eu…
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1
We study the problem of system identification and adaptive control in partially observable linear dynamical systems. Adaptive and closed-loop system identification is a challenging…
Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1
We study the problem of adaptive control in partially observable linear quadratic Gaussian control systems, where the model dynamics are unknown a priori. We propose LqgOpt, a nove…
Semi-Supervised StyleGAN for Disentanglement Learning
Weili Nie, Tero Karras, Animesh Garg +4
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: diffi…