AI Paper Atlas

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

NeurIPS 2017 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
use two-stage thresholded generative estimator instead of l1-regularized logistic regressiongenerative classifier for isotropic Gaussians · synthetic isotropic Gaussians, p-dimensional, 20 trialsexcess 0-1 errorImproved
increase sparsity level s of the true differential parameterdiscriminative l1 logistic regression · synthetic isotropic Gaussianssample complexity burn-inHurt
increase sparsity level s of the true differential parameterthresholded generative estimator · synthetic isotropic Gaussianssample complexity burn-inNo clear effect
add soft-thresholding stage to the generative estimatenaive generative estimator · theory, l2 error of differential parameterl2 error rateImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy