Related papers: Darwinian Data Structure Selection
When employing an evolutionary algorithm to optimize a neural networks architecture, developers face the added challenge of tuning the evolutionary algorithm's own hyperparameters - population size, mutation rate, cloning rate, and number…
Water scarcity and the low quality of wastewater produced in industrial applications present significant challenges, particularly in managing fresh water intake and reusing residual quantities. These issues affect various industries,…
The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…
DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large variation among individual trials as well as the…
This work investigates the selection of high-quality pre-training data from massive corpora to enhance LMs' capabilities for downstream usage. We formulate data selection as a generalized Optimal Control problem, which can be solved…
Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a…
The need for Knowledge and Data Discovery Management Systems (KDDMS) that support ad hoc data mining queries has been long recognized. A significant amount of research has gone into building tightly coupled systems that integrate…
Evolutionary computation has long promised to deliver both high-performance optimization tools as well as rigorous scientific simulations of Darwinian evolution. However, modern algorithms frequently abandon evolutionary fidelity for…
Modern computing paradigms, such as cloud computing, are increasingly adopting GPUs to boost their computing capabilities primarily due to the heterogeneous nature of AI/ML/deep learning workloads. However, the energy consumption of GPUs is…
Differentiable architecture search (DARTS) has emerged as a promising technique for effective neural architecture search, and it mainly contains two steps to find the high-performance architecture: First, the DARTS supernet that consists of…
Differentiable neural architecture search (DARTS), as a gradient-guided search method, greatly reduces the cost of computation and speeds up the search. In DARTS, the architecture parameters are introduced to the candidate operations, but…
In this paper, we tackle an open research question in transfer learning, which is selecting a model initialization to achieve high performance on a new task, given several pre-trained models. We propose a new highly efficient and accurate…
Hierarchical clustering remains a fundamental challenge in data mining, particularly when dealing with large-scale datasets where traditional approaches fail to scale effectively. Recent Chameleon-based algorithms - Chameleon2, M-Chameleon,…
Differentiable architecture search (DARTS) has significantly promoted the development of NAS techniques because of its high search efficiency and effectiveness but suffers from performance collapse. In this paper, we make efforts to…
The effectiveness of in-memory dynamic graph storage (DGS) for supporting concurrent graph read and write queries is crucial for real-time graph analytics and updates. Various methods have been proposed, for example, LLAMA, Aspen,…
Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address efficiency challenges, Dynamic Deep Learning Systems (DDLSs)…
This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy,…
A flexible and highly-extensible data assimilation testing suite, named DATeS, is described in this paper. DATeS aims to offer a unified testing environment that allows researchers to compare different data assimilation methodologies and…
Efficient runtime task scheduling on complex memory hierarchy becomes increasingly important as modern and future High-Performance Computing (HPC) systems are progressively composed of multisocket and multi-chiplet nodes with nonuniform…
Differential Dynamic Microscopy (DDM) is the combination of optical microscopy to statistical analysis to obtain information about the dynamical behaviour of a variety of samples spanning from soft matter physics to biology. In DDM, the…