Related papers: A Sampling Strategy Benchmark for Machine-Learning…
Logistic regression is by far the most widely used classifier in real-world applications. In this paper, we benchmark the state-of-the-art active learning methods for logistic regression and discuss and illustrate their underlying…
We study the problem of efficiently estimating counts for queries involving complex filters, such as user-defined functions, or predicates involving self-joins and correlated subqueries. For such queries, traditional sampling techniques may…
Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…
Recently a likelihood-based methodology has been developed by the Collaboratory for the Study of Earthquake Predictability (CSEP) with a view to testing and ranking seismicity models. We analyze this approach from the standpoint of possible…
To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount of training samples, and data are expected to fully present…
Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However,…
Nowadays, the continuous improvement and automation of industrial processes has become a key factor in many fields, and in the chemical industry, it is no exception. This translates into a more efficient use of resources, reduced production…
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples,…
Machine learning has taken a critical role in seismic interpretation workflows, especially in fault delineation tasks. However, despite the recent proliferation of pretrained models and synthetic datasets, the field still lacks a systematic…
Model merging has emerged as a promising solution to accommodate multiple large models within constrained memory budgets. We present StatsMerging, a novel lightweight learning-based model merging method guided by weight distribution…
To address the modality imbalance caused by data heterogeneity, existing multi-modal learning (MML) approaches primarily focus on balancing this difference from the perspective of optimization objectives. However, almost all existing…
This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. The framework includes the following processes: feature extraction, candidate model labeling, offline training, and online…
In scientific machine learning, models are routinely deployed with parameter values or boundary conditions far from those used in training. This paper studies the learning-where-to-learn problem of designing a training data distribution…
The predictive capabilities of machine learning (ML) models used in materials discovery are typically measured using simple statistics such as the root-mean-square error (RMSE) or the coefficient of determination ($r^2$) between…
Standard supervised learning procedures are validated against a test set that is assumed to have come from the same distribution as the training data. However, in many problems, the test data may have come from a different distribution. We…
Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…
Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress paper, we put the…
The aim of this work was to predict the probability of the spread of rock formations with hydrocarbon-collecting properties in the studied coastal area using a stack of machine learning algorithms and data augmentation and modification…
Increasingly large datasets of robot actions and sensory observations are being collected to train ever-larger neural networks. These datasets are collected based on tasks and while these tasks may be distinct in their descriptions, many…
Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a…