AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Uniform Convergence with Square-Root Lipschitz Loss

Lijia Zhou, Zhen Dai, Frederic Koehler, Nathan Srebro

NeurIPS 2023 · Optimization › Nonconvex and smooth optimization · approach: Langevin sampling for nonconvex problems · 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
Use a nonnegative loss whose square root is Lipschitz instead of requiring the loss to be smoothUniform convergence for Gaussian data · Gaussian multi-index modelsuniform generalization boundImproved
Analyze phase retrieval with the loss (|ŷ|-y)^2Minimal-norm phase-retrieval interpolant · Phase retrievalpopulation loss consistencyImproved
Use a loss that treats positive ReLU labels with squared error and zero labels with σ(ŷ)^2Minimal-norm ReLU interpolant · ReLU regressionpopulation loss consistencyImproved
Apply the uniform-convergence analysis to the minimal nuclear-norm interpolantMatrix sensing · Noisy Gaussian matrix sensingrelative squared Frobenius reconstruction errorImproved
Use a weighted square loss when the non-Gaussian tail depends on the signal through hUniform convergence for dependent non-Gaussian features · Non-Gaussian universality counterexampleweighted population lossImproved
Assume Gaussian universality from covariance matching without accounting for signal-tail dependenceOptimistic-rate generalization analysis · Non-Gaussian featurespopulation squared loss boundHurt

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