Rice University

research

∙ 09/06/2021

A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning

The rapid recent progress in machine learning (ML) has raised a number o...

Yehuda Dar, et al. ∙

research

∙ 02/29/2020

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

Neural-symbolic computing has now become the subject of interest of both...

Luis Lamb, et al. ∙

research

∙ 05/04/2020

Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach

Gradient-domain machine learning (GDML) is an accurate and efficient app...

Jiang Wang, et al. ∙

research

∙ 06/12/2020

MomentumRNN: Integrating Momentum into Recurrent Neural Networks

Designing deep neural networks is an art that often involves an expensiv...

Tan M. Nguyen, et al. ∙

research

∙ 10/15/2021

NeuroView: Explainable Deep Network Decision Making

Deep neural networks (DNs) provide superhuman performance in numerous co...

CJ Barberan, et al. ∙

research

∙ 09/14/2021

Data-Driven Theory-guided Learning of Partial Differential Equations using SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE)

The measured spatiotemporal response of various physical processes is ut...

Sutanu Bhowmick, et al. ∙

research

∙ 07/10/2019

Out-of-Distribution Detection Using Neural Rendering Generative Models

Out-of-distribution (OoD) detection is a natural downstream task for dee...

Yujia Huang, et al. ∙

research

∙ 06/09/2022

Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems

Data assimilation (DA) is a key component of many forecasting models in ...

Ashesh Chattopadhyay, et al. ∙

research

∙ 01/29/2022

Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity

More than 70 of these idle compute are cheap CPUs with few cores that ar...

Minghao Yan, et al. ∙

research

∙ 07/23/2020

Learning Differentiable Programs with Admissible Neural Heuristics

We study the problem of learning differentiable functions expressed as p...

Ameesh Shah, et al. ∙

research

∙ 10/26/2021

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial at...

Yonggan Fu, et al. ∙

research

∙ 03/21/2022

BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art...

Cheng Wan, et al. ∙

research

∙ 04/07/2022

DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors

DeepTensor is a computationally efficient framework for low-rank decompo...

Vishwanath Saragadam, et al. ∙

research

∙ 08/28/2019

Stock Price Forecasting and Hypothesis Testing Using Neural Networks

In this work we use Recurrent Neural Networks and Multilayer Perceptrons...

Kerda Varaku, et al. ∙

research

∙ 05/17/2022

DPO: Dynamic-Programming Optimization on Hybrid Constraints

In Bayesian inference, the most probable explanation (MPE) problem reque...

Vu H. N. Phan, et al. ∙

research

∙ 02/25/2020

Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning

To make weather/climate modeling computationally affordable, small-scale...

Ashesh Chattopadhyay, et al. ∙

research

∙ 08/18/2021

Thermal Image Processing via Physics-Inspired Deep Networks

We introduce DeepIR, a new thermal image processing framework that combi...

Vishwanath Saragadam, et al. ∙

research

∙ 10/01/2021

Closed-form discovery of structural errors in models of chaotic systems by integrating Bayesian sparse regression and data assimilation

Models used for many important engineering and natural systems are imper...

Rambod Mojgani, et al. ∙

research

∙ 10/16/2021

What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression

Recent works have focused on compressing pre-trained language models (PL...

Mengnan Du, et al. ∙

research

∙ 12/14/2021

CLIP-Lite: Information Efficient Visual Representation Learning from Textual Annotations

We propose CLIP-Lite, an information efficient method for visual represe...

Aman Shrivastava, et al. ∙

research

∙ 05/08/2022

DPMS: An ADD-Based Symbolic Approach for Generalized MaxSAT Solving

Boolean MaxSAT, as well as generalized formulations such as Min-MaxSAT a...

Anastasios Kyrillidis, et al. ∙

research

∙ 03/20/2019

Using Local Experiences for Global Motion Planning

Sampling-based planners are effective in many real-world applications su...

Constantinos Chamzas, et al. ∙

research

∙ 02/25/2020

Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors

We study the linear subspace fitting problem in the overparameterized se...

Yehuda Dar, et al. ∙

research

∙ 03/15/2022

LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference

Low precision deep neural network (DNN) training is one of the most effe...

Zhongzhi Yu, et al. ∙

research

∙ 08/30/2020

SOLAR: Sparse Orthogonal Learned and Random Embeddings

Dense embedding models are commonly deployed in commercial search engine...

Tharun Medini, et al. ∙

research

∙ 02/14/2019

WaveletFCNN: A Deep Time Series Classification Model for Wind Turbine Blade Icing Detection

Wind power, as an alternative to burning fossil fuels, is plentiful and ...

Binhang Yuan, et al. ∙

research

∙ 12/17/2019

LTLf Synthesis with Fairness and Stability Assumptions

In synthesis, assumptions are constraints on the environment that rule o...

Shufang Zhu, et al. ∙

research

∙ 07/06/2021

Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections

When a robot performs a task next to a human, physical interaction is in...

Dylan P. Losey, et al. ∙

research

∙ 11/19/2021

FBNetV5: Neural Architecture Search for Multiple Tasks in One Run

Neural Architecture Search (NAS) has been widely adopted to design accur...

Bichen Wu, et al. ∙

research

∙ 12/22/2021

GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art...

Haoran You, et al. ∙

research

∙ 06/19/2020

Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples

Recent work (Ilyas et al, 2019) suggests that adversarial examples are f...

Josue Ortega Caro, et al. ∙

research

∙ 11/14/2020

MP-Boost: Minipatch Boosting via Adaptive Feature and Observation Sampling

Boosting methods are among the best general-purpose and off-the-shelf ma...

Mohammad Taha Toghani, et al. ∙

research

∙ 06/07/2022

Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow

Transfer learning (TL) is becoming a powerful tool in scientific applica...

Adam Subel, et al. ∙

research

∙ 07/21/2022

The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)

Embedding tables dominate industrial-scale recommendation model sizes, u...

Aditya Desai, et al. ∙

research

∙ 05/17/2018

A Spline Theory of Deep Networks (Extended Version)

We build a rigorous bridge between deep networks (DNs) and approximation...

Randall Balestriero, et al. ∙

research

∙ 05/29/2018

Deep Mesh Projectors for Inverse Problems

We develop a new learning-based approach to ill-posed inverse problems. ...

Sidharth Gupta, et al. ∙

research

∙ 06/25/2020

STORM: Foundations of End-to-End Empirical Risk Minimization on the Edge

Empirical risk minimization is perhaps the most influential idea in stat...

Benjamin Coleman, et al. ∙

research

∙ 09/09/2021

Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

We study the problem of generating arithmetic math word problems (MWPs) ...

Zichao Wang, et al. ∙

research

∙ 08/04/2022

Differentially Private Counterfactuals via Functional Mechanism

Counterfactual, serving as one emerging type of model explanation, has a...

Fan Yang, et al. ∙

research

∙ 01/23/2020

Reducing the Representation Error of GAN Image Priors Using the Deep Decoder

Generative models, such as GANs, learn an explicit low-dimensional repre...

Max Daniels, et al. ∙

research

∙ 07/19/2021

Modality Fusion Network and Personalized Attention in Momentary Stress Detection in the Wild

Multimodal wearable physiological data in daily life have been used to e...

Han Yu, et al. ∙

research

∙ 08/27/2021

Convergence Rates for Learning Linear Operators from Noisy Data

We study the Bayesian inverse problem of learning a linear operator on a...

Maarten V. de Hoop, et al. ∙

research

∙ 09/29/2021

Programmable Spectral Filter Arrays for Hyperspectral Imaging

Modulating the spectral dimension of light has numerous applications in ...

Aswin C. Sankaranarayanan, et al. ∙

research

∙ 01/25/2022

Rayleigh EigenDirections (REDs): GAN latent space traversals for multidimensional features

We present a method for finding paths in a deep generative model's laten...

Guha Balakrishnan, et al. ∙

research

∙ 02/07/2022

MINER: Multiscale Implicit Neural Representations

We introduce a new neural signal representation designed for the efficie...

Vishwanath Saragadam, et al. ∙

research

∙ 03/16/2022

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?

Vision transformers (ViTs) have recently set off a new wave in neural ar...

Yonggan Fu, et al. ∙

research

∙ 01/25/2019

Better accuracy with quantified privacy: representations learned via reconstructive adversarial network

The remarkable success of machine learning, especially deep learning, ha...

Sicong Liu, et al. ∙

research

∙ 02/01/2019

Compressing Gradient Optimizers via Count-Sketches

Many popular first-order optimization methods (e.g., Momentum, AdaGrad, ...

Ryan Spring, et al. ∙

research

∙ 07/11/2019

ADDMC: Exact Weighted Model Counting with Algebraic Decision Diagrams

We compute exact literal-weighted model counts of CNF formulas. Our algo...

Jeffrey M. Dudek, et al. ∙

research

∙ 08/13/2019

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics

Continuous control and planning remains a major challenge in robotics an...

Saurabh Daptardar, et al. ∙

Rice University

Featured Researchers