Research map / Probabilistic and scientific modeling / Variational and generative sampling
On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
Adarsh Prasad, Alexandru Niculescu-Mizil, Pradeep K Ravikumar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use two-stage thresholded generative estimator instead of l1-regularized logistic regression | generative classifier for isotropic Gaussians · synthetic isotropic Gaussians, p-dimensional, 20 trials | excess 0-1 error | Improved |
| increase sparsity level s of the true differential parameter | discriminative l1 logistic regression · synthetic isotropic Gaussians | sample complexity burn-in | Hurt |
| increase sparsity level s of the true differential parameter | thresholded generative estimator · synthetic isotropic Gaussians | sample complexity burn-in | No clear effect |
| add soft-thresholding stage to the generative estimate | naive generative estimator · theory, l2 error of differential parameter | l2 error rate | Improved |
Closest papers by meaning
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · similarity 0.87)
- A solvable model of learning generative diffusion: theory and insights (NeurIPS 2025 · similarity 0.86)
- Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates (ICLR 2025 · similarity 0.86)
- When Models Don’t Collapse: On the Consistency of Iterative MLE (NeurIPS 2025 · similarity 0.86)
- Sobolev Regularized MMD Gradient Flow (NeurIPS 2026 · similarity 0.86)
- Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
