Search Results for author:
Found 65 papers, 27 papers with code
Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes and Atmospheric Dynamics
Remarkable progress in the development of Deep Learning Weather Prediction (DLWP) models positions them to become competitive with traditional numerical weather prediction (NWP) models.
Transferring Knowledge from Large Foundation Models to Small Downstream Models
Furthermore, AFT reliably translates improvement in pre-trained models into improvement in downstream performance, even if the downstream model is over $50\times$ smaller, and can effectively transfer complementary information learned by multiple pre-trained models.
Discovering Bias in Latent Space: An Unsupervised Debiasing Approach
The question-answering (QA) capabilities of foundation models are highly sensitive to prompt variations, rendering their performance susceptible to superficial, non-meaning-altering changes.
OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point Clouds
A Colored point cloud, as a simple and efficient 3D representation, has many advantages in various fields, including robotic navigation and scene reconstruction.
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical partial differential equation (PDE) solvers.
Chronos: Learning the Language of Time Series
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models.
Explainable AI for Embedded Systems Design: A Case Study of Static Redundant NVM Memory Write Prediction
To achieve this, we propose a methodology consisting of: 1) the development of relevant ML models for explaining silent store prediction, and 2) the application of XAI to explain these models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Rock Classification Based on Residual Networks
This boosts the model's performance, achieving an accuracy of 73. 7% on the test dataset.
Harnessing Machine Learning for Discerning AI-Generated Synthetic Images
Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques.
Deep Non-Parametric Time Series Forecaster
This paper presents non-parametric baseline models for time series forecasting.
Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale.
VR PreM+ : An Immersive Pre-learning Branching Visualization System for Museum Tours
We present VR PreM+, an innovative VR system designed to enhance web exploration beyond traditional computer screens.
AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting
We introduce AutoGluon-TimeSeries - an open-source AutoML library for probabilistic time series forecasting.
Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks.
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset.
Efficient Task Offloading Algorithm for Digital Twin in Edge/Cloud Computing Environment
In the era of Internet of Things (IoT), Digital Twin (DT) is envisioned to empower various areas as a bridge between physical objects and the digital world.
Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting
Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization.
Manifold Diffusion Fields
Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold.
Neural Network Predicts Ion Concentration Profiles under Nanoconfinement
Overall, our deep learning model is a fast, flexible, and accurate surrogate model to predict ion concentration profiles in nanoconfinement.
Testing Causality for High Dimensional Data
Determining causal relationship between high dimensional observations are among the most important tasks in scientific discoveries.
Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
These results highlight the potential for leveraging denoise pretraining approaches to build more generalizable neural potentials for complex molecular systems.
Backpropagation through Back Substitution with a Backslash
This paper has three contributions: (i) it is of intellectual value to replace traditional treatments of automatic differentiation with a (left acting) operator theoretic, graph-based approach; (ii) operators can be readily placed in matrices in software in programming languages such as Julia as an implementation option; (iii) we introduce a novel notation, ``transpose dot'' operator ``$\{\}^{T_\bullet}$'' that allows for the reversal of operators.
Dataset for predicting cybersickness from a virtual navigation task
This work presents a dataset collected to predict cybersickness in virtual reality environments.
First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting
Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.
Criteria for Classifying Forecasting Methods
Classifying forecasting methods as being either of a "machine learning" or "statistical" nature has become commonplace in parts of the forecasting literature and community, as exemplified by the M4 competition and the conclusion drawn by the organizers.
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function
In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.
MOFormer: Self-Supervised Transformer model for Metal-Organic Framework Property Prediction
Furthermore, we revealed that MOFormer can be more data-efficient on quantum-chemical property prediction than structure-based CGCNN when training data is limited.
Predicting CO$_2$ Absorption in Ionic Liquids with Molecular Descriptors and Explainable Graph Neural Networks
Fingerprint works on graph structure at the feature extraction stage, while GNNs directly handle molecule structure in both the feature extraction and model prediction stage.
On the detrimental effect of invariances in the likelihood for variational inference
Then, we transfer our analysis of the linear model to neural networks.
Graph Neural Networks for Molecules
Graph neural networks (GNNs), which are capable of learning representations from graphical data, are naturally suitable for modeling molecular systems.
TransPolymer: a Transformer-based language model for polymer property predictions
Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer.
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.
Ranked #1 on
Earth Surface Forecasting
on EarthNet2021 OOD Track
Crystal Twins: Self-supervised Learning for Crystalline Material Property Prediction
Machine learning (ML) models have been widely successful in the prediction of material properties.
Robust Probabilistic Time Series Forecasting
Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties.
Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
On most benchmarks, the generic GNN pre-trained by iMolCLR rivals or even surpasses supervised learning models with sophisticated architecture designs and engineered features.
Graph-Relational Domain Adaptation
In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency, e. g., a graph of states in the US with each state as a domain and each edge indicating adjacency, thereby allowing domains to align flexibly based on the graph structure.
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems.
GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics
We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure.
Modeling Advection on Directed Graphs using Matérn Gaussian Processes for Traffic Flow
The transport of traffic flow can be modeled by the advection equation.
AugLiChem: Data Augmentation Library of Chemical Structures for Machine Learning
Inspired by the success of data augmentations in computer vision and natural language processing, we developed AugLiChem: the data augmentation library for chemical structures.
Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR
When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation $V_T$ of the comparator sequence.
Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting
Quantile regression is an effective technique to quantify uncertainty, fit challenging underlying distributions, and often provide full probabilistic predictions through joint learnings over multiple quantile levels.
Deep Explicit Duration Switching Models for Time Series
We propose the Recurrent Explicit Duration Switching Dynamical System (RED-SDS), a flexible model that is capable of identifying both state- and time-dependent switching dynamics.
A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC).
Correcting Exposure Bias for Link Recommendation
Link prediction methods are frequently applied in recommender systems, e. g., to suggest citations for academic papers or friends in social networks.
5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning
The increasing complexity of configuring cellular networks suggests that machine learning (ML) can effectively improve 5G technologies.
Zero-Shot Recommender Systems
This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS.
Variance Reduced Training with Stratified Sampling for Forecasting Models
In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset.
Deep Learning-based Compressive Beam Alignment in mmWave Vehicular Systems
We design fully-connected layers to optimize channel acquisition and beam alignment.
Molecular Contrastive Learning of Representations via Graph Neural Networks
In this work, we present MolCLR: Molecular Contrastive Learning of Representations via Graph Neural Networks (GNNs), a self-supervised learning framework that leverages large unlabeled data (~10M unique molecules).
Domain Adaptation for Time Series Forecasting via Attention Sharing
Recently, deep neural networks have gained increasing popularity in the field of time series forecasting.
Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination
Structure and geometry optimization of nanopores on such materials is beneficial for their performances in real-world engineering applications, like water desalination.
Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization
Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm.
Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems
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.
Intermittent Demand Forecasting with Renewal Processes
Intermittency is a common and challenging problem in demand forecasting.
Site-specific online compressive beam codebook learning in mmWave vehicular communication
Furthermore, based on the CS channel measurements, we develop techniques to update and learn such channel AoD statistics at the BS.
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
Deep learning based forecasting methods have become the methods of choice in many applications of time series prediction or forecasting often outperforming other approaches.
Intermittent Demand Forecasting with Deep Renewal Processes
Intermittent demand, where demand occurrences appear sporadically in time, is a common and challenging problem in forecasting.
GluonTS: Probabilistic Time Series Models in Python
We introduce Gluon Time Series (GluonTS, available at https://gluon-ts. mxnet. io), a library for deep-learning-based time series modeling.
Deep Factors for Forecasting
We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part.
Deep State Space Models for Time Series Forecasting
We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning.
Deep Factors with Gaussian Processes for Forecasting
A large collection of time series poses significant challenges for classical and neural forecasting approaches.
Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecasting
Moreover, we show that the Gini regularized OT problem converges to the classical OT problem, when the Gini regularized problem is considered as a function of {\lambda}, the regularization parame-ter.
Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale
We present a scalable and robust Bayesian inference method for linear state space models.
Infinite Shift-invariant Grouped Multi-task Learning for Gaussian Processes
The paper applies this framework for data where each task is a phase-shifted periodic time series.
