相关论文: Darwinian Data Structure Selection

While machine learning models are typically trained to solve prediction problems, we might often want to use them for optimization problems. For example, given a dataset of proteins and their corresponding fluorescence levels, we might want…

Neural Architecture Search (NAS) is an exciting new field which promises to be as much as a game-changer as Convolutional Neural Networks were in 2012. Despite many great works leading to substantial improvements on a variety of tasks,…

The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniques such as Step-Decaying, Cyclical-Learning, and Warmup to…

In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST). Classic network architectures…

In this work, we extend and generalize our solving strategy, first introduced in [1], based on a greedy optimization algorithm and the alternating direction method (ADM) for nonlinear systems computed with multiple load steps. In…

We propose DFModel, a modeling framework for mapping dataflow computation graphs onto large-scale systems. Mapping a workload to a system requires optimizing dataflow mappings at various levels, including the inter-chip (between chips)…

The Joint Automated Repository for Various Integrated Simulations (JARVIS) infrastructure at the National Institute of Standards and Technology (NIST) is a large-scale collection of curated datasets and tools with more than 80000 materials…

In component shape optimization, the component properties are often evaluated by computationally expensive simulations. Such optimization becomes unfeasible when it is focused on a global search requiring thousands of simulations to be…

There has been considerable research on automated index tuning in database management systems (DBMSs). But the majority of these solutions tune the index configuration by retrospectively making computationally expensive physical design…

Neural Architecture Search (NAS) has emerged as a favoured method for unearthing effective neural architectures. Recent development of large models has intensified the demand for faster search speeds and more accurate search results.…

Differentiable Architecture Search (DARTS) provides a baseline for searching effective network architectures based gradient, but it is accompanied by huge computational overhead in searching and training network architecture. Recently, many…

Recent years have witnessed tremendously improved efficiency of Automated Machine Learning (AutoML), especially Automated Deep Learning (AutoDL) systems, but recent work focuses on tabular, image, or NLP tasks. So far, little attention has…

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…

Data selection improves computational efficiency by choosing informative subsets of training samples. However, existing methods ignore the compute budget, treating data selection and importance evaluation independently of compute budget…

As physical realizations of quantum computers move closer towards practical applications, the need for tools to analyze and verify quantum algorithms grows. Among the algorithms and data structures used to tackle such problems, decision…

Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness. For example, AugMix explores…

Neural architecture search (NAS) methods rely on a search strategy for deciding which architectures to evaluate next and a performance estimation strategy for assessing their performance (e.g., using full evaluations, multi-fidelity…

To tackle the exponentiality associated with NP-hard problems, two paradigms have been proposed. First, Branch & Bound, like Dynamic Programming, achieve efficient exact inference but requires extensive information and analysis about the…

In this paper, we propose Saturn, a new data system to improve the efficiency of multi-large-model training (e.g., during model selection/hyperparameter optimization). We first identify three key interconnected systems challenges for users…

Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset. Most existing dataset pruning methods rely on snapshot-based criteria to identify representative samples, often resulting…