Related papers: Probing the Effect of Selection Bias on Generaliza…

Many automated system analysis techniques (e.g., model checking, model-based testing) rely on first obtaining a model of the system under analysis. System modeling is often done manually, which is often considered as a hindrance to adopt…

Recent research suggests that predictions made by machine-learning models can amplify biases present in the training data. When a model amplifies bias, it makes certain predictions at a higher rate for some groups than expected based on…

One of the major challenges for evaluating the effectiveness of data visualizations and visual analytics tools arises from the fact that different users may be using these tools for different tasks. In this paper, we present a simple…

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical learning require computation of capacity measures, such as VC…

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…

When an analyst or scientist has a belief about how the world works, their thinking can be biased in favor of that belief. Therefore, one bedrock principle of science is to minimize that bias by testing the predictions of one's belief…

This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility.…

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance, but machine systems reliably…

AI-based systems are widely employed nowadays to make decisions that have far-reaching impacts on individuals and society. Their decisions might affect everyone, everywhere and anytime, entailing concerns about potential human rights…

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

Quantification is the supervised learning task that consists of training predictors of the class prevalence values of sets of unlabelled data, and is of special interest when the labelled data on which the predictor has been trained and the…

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

In high-stakes domains like healthcare, users often expect that sharing personal information with machine learning systems will yield tangible benefits, such as more accurate diagnoses and clearer explanations of contributing factors.…

Over-parameterized models can perfectly learn various types of data distributions, however, generalization error is usually lower for real data in comparison to artificial data. This suggests that the properties of data distributions have…

As visualization researchers evaluate the impact of visualization design on decision-making, they often hold a one-dimensional perspective on the cognitive processes behind making a decision. Several psychological and economical researchers…

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Diffusion models are powerful generative models that produce high-quality samples from complex data. While their infinite-data behavior is well understood, their generalization with finite data remains less clear. Classical learning theory…