Generative Classifiers Outperform Discriminative Ones on Distribution Shift
Research Paper#Generative Models, Classification, Distribution Shift🔬 Research|Analyzed: Jan 3, 2026 06:13•
Published: Dec 31, 2025 18:31
•1 min read
•ArXivAnalysis
This paper addresses a critical problem in machine learning: the vulnerability of discriminative classifiers to distribution shifts due to their reliance on spurious correlations. It proposes and demonstrates the effectiveness of generative classifiers as a more robust alternative. The paper's significance lies in its potential to improve the reliability and generalizability of AI models, especially in real-world applications where data distributions can vary.
Key Takeaways
- •Discriminative classifiers often fail under distribution shift due to reliance on spurious correlations.
- •Generative classifiers, using class-conditional generative models, are proposed as a more robust alternative.
- •Diffusion-based and autoregressive generative classifiers achieve state-of-the-art performance on distribution shift benchmarks.
- •Generative classifiers reduce the impact of spurious correlations in realistic applications.
- •The paper provides analysis of generative classifier inductive biases and data properties for optimal performance.
Reference / Citation
View Original"Generative classifiers...can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones."