Related papers: Training Data Influence Analysis and Estimation: A…

Choice of training data distribution greatly influences model behavior. Yet, in large-scale settings, precisely characterizing how changes in training data affects predictions is often difficult due to model training costs. Current practice…

Sub-sampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the…

Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the…

Data augmentation has been widely used in machine learning for natural language processing and computer vision tasks to improve model performance. However, little research has studied data augmentation on graph neural networks, particularly…

This paper discusses the fundamental principles of causal inference - the area of statistics that estimates the effect of specific occurrences, treatments, interventions, and exposures on a given outcome from experimental and observational…

Selecting appropriate training data is crucial for effective instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across a diverse range of tasks.…

Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models are expensive to train and difficult to parameterize. Objective: We investigate methodological issues for designing and evaluating…

How can we model influence between individuals in a social system, even when the network of interactions is unknown? In this article, we review the literature on the "influence model," which utilizes independent time series to estimate how…

Influence propagation in social networks has recently received large interest. In fact, the understanding of how influence propagates among subjects in a social network opens the way to a growing number of applications. Many efforts have…

Classical causal and statistical inference methods typically assume the observed data consists of independent realizations. However, in many applications this assumption is inappropriate due to a network of dependences between units in the…

The successful completion of a software development process depends on the analytical capability and foresightedness of the project manager. For the project manager, the main intriguing task is to manage the risk factors as they adversely…

This thesis explores how deep learning models learn over time, using ideas inspired by force analysis. Specifically, we zoom in on the model's training procedure to see how one training example affects another during learning, like…

Whether future AI models are fair, trustworthy, and aligned with the public's interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few…

Mixed-effect models are flexible tools for researchers in a myriad of fields, but that flexibility comes at the cost of complexity and if users are not careful in how their model is specified, they could be making faulty inferences from…

Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving…

Estimating how a treatment affects different individuals, known as heterogeneous treatment effect estimation, is an important problem in empirical sciences. In the last few years, there has been a considerable interest in adapting machine…

As artificial intelligence and machine learning tools become more accessible, and scientists face new obstacles to data collection (e.g. rising costs, declining survey response rates), researchers increasingly use predictions from…

Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how…

Understanding the behaviors of information propagation is essential for the effective exploitation of social influence in social networks. However, few existing influence models are both tractable and efficient for describing the…

Understanding the behaviors of information propagation is essential for the effective exploitation of social influence in social networks. However, few existing influence models are tractable and efficient for describing the information…