We evaluate the use of the open-source Llama-2 model for generating
well...
The ability to learn continuously from an incoming data stream without
c...
Hyperparameter optimization (HPO) is crucial for fine-tuning machine lea...
Graph Neural Networks (GNNs) have emerged as a prominent class of data-d...
We evaluate AI-assisted generative capabilities on fundamental numerical...
A computational workflow, also known as workflow, consists of tasks that...
Continual learning (CL) is a field concerned with learning a series of
i...
As we enter the exascale computing era, efficiently utilizing power and
...
Modern computational methods, involving highly sophisticated mathematica...
Classical problems in computational physics such as data-driven forecast...
Natural language processing (NLP) is a promising approach for analyzing ...
Robust machine learning models with accurately calibrated uncertainties ...
Distributed data storage services tailored to specific applications have...
Accurate traffic forecasting is vital to an intelligent transportation
s...
Bayesian optimization (BO) is a widely used approach for computationally...
In many computational science and engineering applications, the output o...
Deep neural network ensembles that appeal to model diversity have been u...
I/O efficiency is crucial to productivity in scientific computing, but t...
Deep-learning-based data-driven forecasting methods have produced impres...
The information bottleneck framework provides a systematic approach to l...
Deep reinforcement learning (DRL) is a promising outer-loop intelligence...
Using the data from loop detector sensors for near-real-time detection o...
We consider nonlinear optimization problems that involve surrogate model...
Deep neural networks are powerful predictors for a variety of tasks. How...
The problem of phase retrieval, or the algorithmic recovery of lost phas...
We formulate the continual learning (CL) problem via dynamic programming...
Polly is the LLVM project's polyhedral loop nest optimizer. Recently,
us...
In this paper, we develop a ytopt autotuning framework that leverages
Ba...
In this paper we consider the problem of learning a regression function
...
Non-orthogonal multiple access (NOMA) is a key technology to enable mass...
Developing high-performing predictive models for large tabular data sets...
An autotuning is an approach that explores a search space of possible
im...
Wide area networking infrastructures (WANs), particularly science and
re...
Predicting the properties of a molecule from its structure is a challeng...
Meta-continual learning algorithms seek to rapidly train a model when fa...
We focus on the problem of how to achieve online continual learning unde...
The canonical solution methodology for finite constrained Markov decisio...
If edge devices are to be deployed to critical applications where their
...
Highway traffic modeling and forecasting approaches are critical for
int...
In this paper, we apply the Non-Orthogonal Multiple Access (NOMA) techni...
Quantum computing is a computational paradigm with the potential to
outp...
Quantum computing exploits basic quantum phenomena such as state
superpo...
Computer-assisted synthesis planning aims to help chemists find better
r...
Strong gravitational lensing of astrophysical sources by foreground gala...
Traffic forecasting approaches are critical to developing adaptive strat...
Optimal engine operation during a transient driving cycle is the key to
...
Rapid simulations of advection-dominated problems are vital for multiple...
We introduce the Balsam service to manage high-throughput task schedulin...
Cancer is a complex disease, the understanding and treatment of which ar...
The ability to learn and adapt in real time is a central feature of
biol...