Open Problem: Learning with Variational Objectives on Measures
Not on the map. Why?
Abstract (arXiv)
The theory of statistical learning has focused on variational objectives expressed on functions. In this note, we discuss motivations to write similar objectives on measures, in particular to discuss out-of-distribution generalization and weakly-supervised learning. It raises a natural question: can one cast usual statistical learning results to objectives expressed on measures? Does the resulting construction lead to new algorithms of practical interest?
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 41 references that are in the map. First posted on arXiv 20 Jun 2023.
Builds on
12 of 41 references.
References · 12
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2023GPT-4 Technical Reportcited by 18,396
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
- 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
- 2017Multi-task Self-Supervised Visual Learningcited by 200
- 2019A General Theory for Structured Prediction with Smooth Convex Surrogatescited by 14
- 2022Epi-Convergence of Expectation Functions under Varying Measures and Integrandscited by 2
Built on by
Not cited yet.