no code implementations • 3 Apr 2024 • Yaozhong Shi, Angela F. Gao, Zachary E. Ross, Kamyar Azizzadenesheli
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.
1 code implementation • 19 Mar 2024 • Md Ashiqur Rahman, Robert Joseph George, Mogab Elleithy, Daniel Leibovici, Zongyi Li, Boris Bonev, Colin White, Julius Berner, Raymond A. Yeh, Jean Kossaifi, Kamyar Azizzadenesheli, Anima Anandkumar
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 $36\%$.
no code implementations • 26 Feb 2024 • Miguel Liu-Schiaffini, Julius Berner, Boris Bonev, Thorsten Kurth, Kamyar Azizzadenesheli, Anima Anandkumar
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.
no code implementations • 2 Feb 2024 • Ziqi Ma, Kamyar Azizzadenesheli, Anima Anandkumar
Operator learning has been increasingly adopted in scientific and engineering applications, many of which require calibrated uncertainty quantification.
no code implementations • 19 Jan 2024 • Minkai Xu, Jiaqi Han, Aaron Lou, Jean Kossaifi, Arvind Ramanathan, Kamyar Azizzadenesheli, Jure Leskovec, Stefano Ermon, Anima Anandkumar
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.
no code implementations • 29 Sep 2023 • Jean Kossaifi, Nikola Kovachki, Kamyar Azizzadenesheli, Anima Anandkumar
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.
no code implementations • 27 Sep 2023 • Kamyar Azizzadenesheli, Nikola Kovachki, Zongyi Li, Miguel Liu-Schiaffini, Jean Kossaifi, Anima Anandkumar
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.
1 code implementation • 7 Sep 2023 • Yaozhong Shi, Grigorios Lavrentiadis, Domniki Asimaki, Zachary E. Ross, Kamyar Azizzadenesheli
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.
no code implementations • 17 Aug 2023 • Miguel Liu-Schiaffini, Clare E. Singer, Nikola Kovachki, Tapio Schneider, Kamyar Azizzadenesheli, Anima Anandkumar
Tipping points are abrupt, drastic, and often irreversible changes in the evolution of non-stationary and chaotic dynamical systems.
1 code implementation • 27 Jul 2023 • Colin White, Renbo Tu, Jean Kossaifi, Gennady Pekhimenko, Kamyar Azizzadenesheli, Anima Anandkumar
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.
1 code implementation • 17 Jul 2023 • Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, Yuqing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
1 code implementation • 29 May 2023 • Haque Ishfaq, Qingfeng Lan, Pan Xu, A. Rupam Mahmood, Doina Precup, Anima Anandkumar, Kamyar Azizzadenesheli
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.
no code implementations • 14 Feb 2023 • Jae Hyun Lim, Nikola B. Kovachki, Ricardo Baptista, Christopher Beckham, Kamyar Azizzadenesheli, Jean Kossaifi, Vikram Voleti, Jiaming Song, Karsten Kreis, Jan Kautz, Christopher Pal, Arash Vahdat, Anima Anandkumar
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.
no code implementations • 25 Nov 2022 • Md Ashiqur Rahman, Jasorsi Ghosh, Hrishikesh Viswanath, Kamyar Azizzadenesheli, Aniket Bera
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.
1 code implementation • 24 Nov 2022 • Hongkai Zheng, Weili Nie, Arash Vahdat, Kamyar Azizzadenesheli, Anima Anandkumar
Diffusion models have found widespread adoption in various areas.
no code implementations • 31 Oct 2022 • Gege Wen, Zongyi Li, Qirui Long, Kamyar Azizzadenesheli, Anima Anandkumar, Sally M. Benson
Carbon capture and storage (CCS) plays an essential role in global decarbonization.
no code implementations • 21 Sep 2022 • Audrey Huang, Liu Leqi, Zachary Chase Lipton, Kamyar Azizzadenesheli
To mitigate these problems, we incorporate model-based estimation to develop the first doubly robust (DR) estimator for the CDF of returns in MDPs.
no code implementations • 12 Jul 2022 • Victor D. Dorobantu, Kamyar Azizzadenesheli, Yisong Yue
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).
no code implementations • 27 Jun 2022 • Liu Leqi, Audrey Huang, Zachary C. Lipton, Kamyar Azizzadenesheli
Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class.
1 code implementation • 22 Jun 2022 • Pan Xu, Hongkai Zheng, Eric Mazumdar, Kamyar Azizzadenesheli, Anima Anandkumar
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.
no code implementations • 17 Jun 2022 • Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi
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.
no code implementations • 3 Jun 2022 • Sahin Lale, Yuanyuan Shi, Guannan Qu, Kamyar Azizzadenesheli, Adam Wierman, Anima Anandkumar
However, current reinforcement learning (RL) methods lack stabilization guarantees, which limits their applicability for the control of safety-critical systems.
1 code implementation • 28 May 2022 • Qian Zhang, Anuran Makur, Kamyar Azizzadenesheli
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.
1 code implementation • 27 May 2022 • Abhijeet Vyas, Kamyar Azizzadenesheli
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.
1 code implementation • 13 May 2022 • Michael O'Connell, Guanya Shi, Xichen Shi, Kamyar Azizzadenesheli, Anima Anandkumar, Yisong Yue, Soon-Jo Chung
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.
2 code implementations • 6 May 2022 • Md Ashiqur Rahman, Manuel A. Florez, Anima Anandkumar, Zachary E. Ross, Kamyar Azizzadenesheli
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.
1 code implementation • 23 Apr 2022 • Md Ashiqur Rahman, Zachary E. Ross, Kamyar Azizzadenesheli
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.
4 code implementations • 22 Feb 2022 • Jaideep Pathak, Shashank Subramanian, Peter Harrington, Sanjeev Raja, Ashesh Chattopadhyay, Morteza Mardani, Thorsten Kurth, David Hall, Zongyi Li, Kamyar Azizzadenesheli, Pedram Hassanzadeh, Karthik Kashinath, Animashree Anandkumar
FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor.
4 code implementations • 6 Nov 2021 • Zongyi Li, Hongkai Zheng, Nikola Kovachki, David Jin, Haoxuan Chen, Burigede Liu, Kamyar Azizzadenesheli, Anima Anandkumar
Specifically, in PINO, we combine coarse-resolution training data with PDE constraints imposed at a higher resolution.
1 code implementation • 3 Sep 2021 • Gege Wen, Zongyi Li, Kamyar Azizzadenesheli, Anima Anandkumar, Sally M. Benson
Here we present U-FNO, a novel neural network architecture for solving multiphase flow problems with superior accuracy, speed, and data efficiency.
no code implementations • 26 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.
1 code implementation • 19 Aug 2021 • Nikola Kovachki, Zongyi Li, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets.
no code implementations • 11 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.
2 code implementations • 13 Jun 2021 • Zongyi Li, Miguel Liu-Schiaffini, Nikola Kovachki, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
Chaotic systems are notoriously challenging to predict because of their sensitivity to perturbations and errors due to time stepping.
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.
no code implementations • 31 May 2021 • Jafar Abbaszadeh Chekan, Kamyar Azizzadenesheli, Cedric Langbort
Adaptively controlling and minimizing regret in unknown dynamical systems while controlling the growth of the system state is crucial in real-world applications.
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.
no code implementations • 4 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.
no code implementations • 10 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.
1 code implementation • 9 Jan 2021 • Jonathan D. Smith, Zachary E. Ross, Kamyar Azizzadenesheli, Jack B. Muir
We introduce a scheme for probabilistic hypocenter inversion with Stein variational inference.
1 code implementation • 29 Nov 2020 • Kamyar Azizzadenesheli
We deploy these estimators and provide generalization bounds in the unlabeled target domain.
17 code implementations • ICLR 2021 • Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces.
no code implementations • 23 Jul 2020 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems.
Model-based Reinforcement Learning reinforcement-learning +1
1 code implementation • 28 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.
4 code implementations • 18 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.
4 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.
1 code implementation • 1 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.
1 code implementation • 25 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.
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.
no code implementations • 12 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.
6 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.
no code implementations • 31 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.
no code implementations • 30 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.
no code implementations • 25 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).
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.
no code implementations • 28 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.
2 code implementations • 19 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.
no code implementations • 18 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.
3 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.
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.
1 code implementation • ICLR 2018 • Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, Anima Anandkumar
Neural networks are known to be vulnerable to adversarial examples.
3 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.
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.
no code implementations • ICLR 2018 • Zachary C. Lipton, Kamyar Azizzadenesheli, Abhishek Kumar, Lihong Li, Jianfeng Gao, Li Deng
Many practical reinforcement learning problems contain catastrophic states that the optimal policy visits infrequently or never.
no code implementations • ICLR 2018 • Jeremy Bernstein, Kamyar Azizzadenesheli, Yu-Xiang Wang, Anima Anandkumar
The sign stochastic gradient descent method (signSGD) utilizes only the sign of the stochastic gradient in its updates.
no code implementations • 7 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.
no code implementations • 11 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.
no code implementations • 3 Nov 2016 • Zachary C. Lipton, Kamyar Azizzadenesheli, Abhishek Kumar, Lihong Li, Jianfeng Gao, Li Deng
We introduce intrinsic fear (IF), a learned reward shaping that guards DRL agents against periodic catastrophes.
no code implementations • 17 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.
no code implementations • 25 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.