Search Results for author: Rose Yu

Found 58 papers, 36 papers with code

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

1 code implementation3 Jun 2023 Salva Rühling Cachay, Bo Zhao, Hailey James, Rose Yu

While diffusion models can successfully generate data and make predictions, they are predominantly designed for static images.

Inductive Bias

Improving Convergence and Generalization Using Parameter Symmetries

no code implementations22 May 2023 Bo Zhao, Robert M. Gower, Robin Walters, Rose Yu

In this paper, we show that teleportation not only speeds up optimization in the short-term, but gives overall faster time to convergence.


Disentangled Multi-Fidelity Deep Bayesian Active Learning

1 code implementation7 May 2023 Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Yian Ma, Rose Yu

To balance quality and cost, various domain areas of science and engineering run simulations at multiple levels of sophistication.

Active Learning Gaussian Processes

Long-term Forecasting with TiDE: Time-series Dense Encoder

2 code implementations17 Apr 2023 Abhimanyu Das, Weihao Kong, Andrew Leach, Shaan Mathur, Rajat Sen, Rose Yu

Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting.

Time Series Time Series Forecasting

Understanding why shooters shoot -- An AI-powered engine for basketball performance profiling

1 code implementation17 Mar 2023 Alejandro Rodriguez Pascual, Ishan Mehta, Muhammad Khan, Frank Rodriz, Rose Yu

It is crucial that the performance profiles can reflect the diverse playstyles, as well as the fast-changing dynamics of the game.

Generative Adversarial Symmetry Discovery

1 code implementation1 Feb 2023 Jianke Yang, Robin Walters, Nima Dehmamy, Rose Yu

Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori.

Inductive Bias Trajectory Prediction

On the Connection Between MPNN and Graph Transformer

1 code implementation27 Jan 2023 Chen Cai, Truong Son Hy, Rose Yu, Yusu Wang

Graph Transformer (GT) recently has emerged as a new paradigm of graph learning algorithms, outperforming the previously popular Message Passing Neural Network (MPNN) on multiple benchmarks.

Graph Classification Graph Learning +2

Copula Conformal Prediction for Multi-step Time Series Forecasting

no code implementations6 Dec 2022 Sophia Sun, Rose Yu

Accurate uncertainty measurement is a key step to building robust and reliable machine learning systems.

Conformal Prediction Time Series +1

Symmetries, flat minima, and the conserved quantities of gradient flow

1 code implementation31 Oct 2022 Bo Zhao, Iordan Ganev, Robin Walters, Rose Yu, Nima Dehmamy

Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys.

Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts

1 code implementation7 Oct 2022 Rui Wang, Yihe Dong, Sercan Ö. Arik, Rose Yu

Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs).

Time Series Time Series Forecasting

Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

no code implementations19 Jun 2022 Rui Wang, Robin Walters, Rose Yu

In this work, we derive the generalization bounds for data augmentation and equivariant networks, characterizing their effect on learning in a unified framework.

Data Augmentation Generalization Bounds

LIMO: Latent Inceptionism for Targeted Molecule Generation

1 code implementation17 Jun 2022 Peter Eckmann, Kunyang Sun, Bo Zhao, Mudong Feng, Michael K. Gilson, Rose Yu

We corroborate these docking-based results with more accurate molecular dynamics-based calculations of absolute binding free energy and show that one of our generated drug-like compounds has a predicted $K_D$ (a measure of binding affinity) of $6 \cdot 10^{-14}$ M against the human estrogen receptor, well beyond the affinities of typical early-stage drug candidates and most FDA-approved drugs to their respective targets.

Drug Discovery Gaussian Processes +1

Multi-fidelity Hierarchical Neural Processes

1 code implementation10 Jun 2022 Dongxia Wu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu

MF-HNP is flexible enough to handle non-nested high dimensional data at different fidelity levels with varying input and output dimensions.

Epidemiology Gaussian Processes

Faster Optimization on Sparse Graphs via Neural Reparametrization

no code implementations26 May 2022 Nima Dehmamy, Csaba Both, Jianzhi Long, Rose Yu

In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computationally expensive.

Symmetry Teleportation for Accelerated Optimization

1 code implementation21 May 2022 Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu

Experimentally, we show that teleportation improves the convergence speed of gradient descent and AdaGrad for several optimization problems including test functions, multi-layer regressions, and MNIST classification.

Second-order methods

Probabilistic Symmetry for Multi-Agent Dynamics

1 code implementation4 May 2022 Sophia Sun, Robin Walters, Jinxi Li, Rose Yu

We propose a novel deep dynamics model, Probabilistic Equivariant Continuous COnvolution (PECCO) for probabilistic prediction of multi-agent trajectories.

Autonomous Driving Decision Making +2

Taming the Long Tail of Deep Probabilistic Forecasting

no code implementations27 Feb 2022 Jedrzej Kozerawski, Mayank Sharan, Rose Yu

We present two moment-based tailedness measurement concepts to improve performance on the difficult tail examples: Pareto Loss and Kurtosis Loss.

Time Series Time Series Analysis +1

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

1 code implementation28 Jan 2022 Rui Wang, Robin Walters, Rose Yu

Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling.

Inductive Bias

Neural Point Process for Learning Spatiotemporal Event Dynamics

1 code implementation12 Dec 2021 ZiHao Zhou, Xingyi Yang, Ryan Rossi, Handong Zhao, Rose Yu

The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process.

Point Processes Variational Inference

Accelerating Optimization using Neural Reparametrization

no code implementations29 Sep 2021 Nima Dehmamy, Csaba Both, Jianzhi Long, Rose Yu

We tackle the problem of accelerating certain optimization problems related to steady states in ODE and energy minimization problems common in physics.

Automatic Symmetry Discovery with Lie Algebra Convolutional Network

1 code implementation NeurIPS 2021 Nima Dehmamy, Robin Walters, Yanchen Liu, Dashun Wang, Rose Yu

Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups.

Physics-Guided Deep Learning for Dynamical Systems: A Survey

no code implementations2 Jul 2021 Rui Wang, Rose Yu

Modeling complex physical dynamics is a fundamental task in science and engineering.

Deep Bayesian Active Learning for Accelerating Stochastic Simulation

1 code implementation5 Jun 2021 Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu

We propose Interactive Neural Process (INP), a deep Bayesian active learning framework for learning deep surrogate models to accelerate stochastic simulations.

Active Learning

Traffic Forecasting using Vehicle-to-Vehicle Communication

1 code implementation12 Apr 2021 Steven Wong, Lejun Jiang, Robin Walters, Tamás G. Molnár, Gábor Orosz, Rose Yu

In order to best utilize real-world V2V communication data, we integrate first principle models with deep learning.

Generator Surgery for Compressed Sensing

no code implementations22 Feb 2021 Niklas Smedemark-Margulies, Jung Yeon Park, Max Daniels, Rose Yu, Jan-Willem van de Meent, Paul Hand

We introduce a method for achieving low representation error using generators as signal priors.

Meta-Learning Dynamics Forecasting Using Task Inference

1 code implementation20 Feb 2021 Rui Wang, Robin Walters, Rose Yu

DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain.


Lie Algebra Convolutional Neural Networks with Automatic Symmetry Extraction

no code implementations1 Jan 2021 Nima Dehmamy, Yanchen Liu, Robin Walters, Rose Yu

We propose to learn the symmetries during the training of the group equivariant architectures.

Neural Point Process for Forecasting Spatiotemporal Events

no code implementations1 Jan 2021 ZiHao Zhou, Xingyi Yang, Xinyi He, Ryan Rossi, Handong Zhao, Rose Yu

To the best of our knowledge, this is the first neural point process model that can jointly predict both the space and time of events.

Density Estimation Point Processes

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

3 code implementations20 Nov 2020 Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu

While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.

Trajectory Prediction using Equivariant Continuous Convolution

no code implementations ICLR 2021 Robin Walters, Jinxi Li, Rose Yu

Trajectory prediction is a critical part of many AI applications, for example, the safe operation of autonomous vehicles.

Autonomous Vehicles Trajectory Prediction

Deep Imitation Learning for Bimanual Robotic Manipulation

1 code implementation NeurIPS 2020 Fan Xie, Alexander Chowdhury, M. Clara De Paolis Kaluza, Linfeng Zhao, Lawson L. S. Wong, Rose Yu

Compared to baselines, our model generalizes better and achieves higher success rates on several simulated bimanual robotic manipulation tasks.

Imitation Learning

Dynamic Relational Inference in Multi-Agent Trajectories

no code implementations16 Jul 2020 Ruichao Xiao, Manish Kumar Singh, Rose Yu

Neural relational inference (NRI) is a deep generative model that can reason about relations in complex dynamics without supervision.

Learning Disentangled Representations of Video with Missing Data

1 code implementation23 Jun 2020 Armand Comas-Massagué, Chi Zhang, Zlatan Feric, Octavia Camps, Rose Yu

Missing data poses significant challenges while learning representations of video sequences.

Finding Patient Zero: Learning Contagion Source with Graph Neural Networks

no code implementations21 Jun 2020 Chintan Shah, Nima Dehmamy, Nicola Perra, Matteo Chinazzi, Albert-László Barabási, Alessandro Vespignani, Rose Yu

% We observe that GNNs can identify P0 close to the theoretical bound on accuracy, without explicit input of dynamics or its parameters.

Aortic Pressure Forecasting with Deep Sequence Learning

no code implementations12 May 2020 Eliza Huang, Rui Wang, Uma Chandrasekaran, Rose Yu

The aim of this study was to forecast the mean aortic pressure five minutes in advance, using the 25 Hz time series data of previous five minutes as input.

Time Series Time Series Analysis

Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis

1 code implementation ICML 2020 Jung Yeon Park, Kenneth Theo Carr, Stephan Zheng, Yisong Yue, Rose Yu

Efficient and interpretable spatial analysis is crucial in many fields such as geology, sports, and climate science.

Incorporating Symmetry into Deep Dynamics Models for Improved Generalization

1 code implementation ICLR 2021 Rui Wang, Robin Walters, Rose Yu

Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers.

Towards Physics-informed Deep Learning for Turbulent Flow Prediction

1 code implementation20 Nov 2019 Rui Wang, Karthik Kashinath, Mustafa Mustafa, Adrian Albert, Rose Yu

While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models.

Neural Lander: Stable Drone Landing Control using Learned Dynamics

2 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.

Multi-resolution Tensor Learning for Large-Scale Spatial Data

no code implementations19 Feb 2018 Stephan Zheng, Rose Yu, Yisong Yue

High-dimensional tensor models are notoriously computationally expensive to train.


Long-term Forecasting using Tensor-Train RNNs

no code implementations ICLR 2018 Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue

We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics.

Long-term Forecasting using Higher Order Tensor RNNs

1 code implementation ICLR 2018 Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue

We present Higher-Order Tensor RNN (HOT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics.

Time Series Time Series Analysis

Tensor Regression Meets Gaussian Processes

no code implementations31 Oct 2017 Rose Yu, Guangyu Li, Yan Liu

Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention.

Bayesian Inference Gaussian Processes +1

Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

no code implementations25 Oct 2016 Paroma Varma, Bryan He, Dan Iter, Peng Xu, Rose Yu, Christopher De Sa, Christopher Ré

Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set.

Relation Extraction

Learning from Multiway Data: Simple and Efficient Tensor Regression

no code implementations8 Jul 2016 Rose Yu, Yan Liu

In this paper, we introduce subsampled tensor projected gradient to solve the problem.

Multi-Task Learning regression

A Survey on Social Media Anomaly Detection

no code implementations6 Jan 2016 Rose Yu, Huida Qiu, Zhen Wen, Ching-Yung Lin, Yan Liu

In this paper, we present a survey on existing approaches to address this problem.

Anomaly Detection

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