AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Learning a 1-layer conditional generative model in total variation

Ajil Jalal, Justin Kang, Ananya Uppal, Kannan Ramchandran, Eric Price

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: Hardness of learning neural networks · 0 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
replace x ~ N(0, I_k) with x drawn from i.i.d. standard LaplaceMLE for 1-layer conditional generative model · synthetic, k=5 and k=20TV distanceNo clear effect
increase number of samples nMLE · synthetic, TV vs nTV distanceImproved
increase input dimension kMLE · synthetic, n=10^3 and 10^4TV distanceHurt
make bias b more negative so more samples are truncated, MLE using truncated samplesMLE · d=3, x=1, y=phi(eta+b1)TV distanceImproved
use baseline of [35] instead of MLE as bias b decreasesbaseline of [35] · d=3, truncated outputsTV distanceHurt
increase condition number of covariance Sigma*MLE · d=3, b=1TV distanceNo clear effect
increase condition number of covariance Sigma*baseline of [35] · d=3, b=1TV distanceHurt

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