Nir Yosef — accepted AI-conference papers

2025

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Pierre Boyeau, Anastasios Nikolas Angelopoulos, Tianle Li, Nir Yosef, Jitendra Malik, Michael I. Jordan

ICML 2025poster

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically pr…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2020

Decision-Making with Auto-Encoding Variational Bayes

Romain Lopez, Pierre Boyeau, Nir Yosef, Michael I. Jordan, Jeffrey Regier

NeurIPS 2020poster

To make decisions based on a model fit with auto-encoding variational Bayes (AEVB), practitioners often let the variational distribution serve as a surrogate for the posterior distribution. This approach yields biased estimates of the expected risk, and therefore leads to poor decisions for two reas…

Cited by 57 Source ↗PDF ↗code ↗Scholar ↗

2018

Information Constraints on Auto-Encoding Variational Bayes

Romain Lopez, Jeffrey Regier, Michael I Jordan, Nir Yosef

NeurIPS 2018poster

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess structural constraints such as conditional independence. We p…

Cited by 172 Source ↗PDF ↗Scholar ↗