Search Results for author:
Found 11 papers, 5 papers with code
RadEdit: stress-testing biomedical vision models via diffusion image editing
Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing.
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in ultra low-data regimes
Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem.
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
In light of our theoretical studies, we introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising.
Synthetic data, real errors: how (not) to publish and use synthetic data
Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs.
Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data
Generating synthetic data through generative models is gaining interest in the ML community and beyond.
Membership Inference Attacks against Synthetic Data through Overfitting Detection
In this work we argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution.
Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes
It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences.
What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models.
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data.
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
In this paper, we introduce a 3-dimensional evaluation metric, ($\alpha$-Precision, $\beta$-Recall, Authenticity), that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion.
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models
The first approach is an online method which is effective at removing skew at the expense of stereotype.
