Related papers: A Bayesian Approach to Identifying Representationa…

Generative Adversarial Networks (GANs) are popular tools for generative modeling. The dynamics of their adversarial learning give rise to convergence pathologies during training such as mode and discriminator collapse. In machine learning,…

Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation. Since they are parameterized by deep learning models, they are often sensitive to distribution…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

Incomplete data are common in real-world applications. Sensors fail, records are inconsistent, and datasets collected from different sources often differ in scale, sampling rate, and quality. These differences create missing values that…

Data generation and analysis is a fundamental aspect of many industries and disciplines, from strategic decision making in business to research in the physical and social sciences. However, data generated using software and algorithms can…

We introduce GEDI, a Bayesian framework that combines existing self-supervised learning objectives with likelihood-based generative models. This framework leverages the benefits of both GEnerative and DIscriminative approaches, resulting in…

We propose an Gaussian Mixture Model (GMM) learning algorithm, based on our previous work of GMM expansion idea. The new algorithm brings more robustness and simplicity than classic Expectation Maximization (EM) algorithm. It also improves…

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling…

Gaussian graphical models are widely used to represent conditional dependence among random variables. In this paper, we propose a novel estimator for data arising from a group of Gaussian graphical models that are themselves dependent. A…

Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This is particularly concerning with the increasing use of large, unsupervised datasets for training foundational…

Researchers now routinely use AI or other machine learning methods to estimate latent variables of economic interest, then plug-in the estimates as covariates in a regression. We show both theoretically and empirically that naively treating…

Heralded by the initial success in speech recognition and image classification, learning-based approaches with neural networks, commonly referred to as deep learning, have spread across various fields. A primitive form of a neural network…

When using the finite element method (FEM) in inverse problems, its discretization error can produce parameter estimates that are inaccurate and overconfident. The Bayesian finite element method (BFEM) provides a probabilistic model for the…

Modern computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low expected error overall but high error on atypical groups of…

Understanding how well a deep generative model captures a distribution of high-dimensional data remains an important open challenge. It is especially difficult for certain model classes, such as Generative Adversarial Networks and Diffusion…

The increasing use of generative AI for resume screening is predicated on the assumption that it offers an unbiased alternative to biased human decision-making. However, this belief fails to address a critical question: are these AI systems…

\noindent Hyper-parameter selection is a central practical problem in modern machine learning, governing regularization strength, model capacity, and robustness choices. Cross-validation is often computationally prohibitive at scale, while…

The standard approach to answering an identifiable causal-effect query (e.g., $P(Y|do(X)$) when given a causal diagram and observational data is to first generate an estimand, or probabilistic expression over the observable variables, which…

The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly…