AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of learning distributions · 2 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
Smooth the loss landscape during online SGDOnline SGD for single-index models · Single-index models with information exponent k*sample complexity: d^{k^\star-1} -> d^{k^\star/2}Improved
Use λ = O(1), equivalent to zero smoothing (ablation)Smoothed online SGD · Single-index models with information exponent k*sample complexity: d^{k^\star/2} -> d^{k^\star-1}Hurt
Set smoothing to λ = d^{1/4} (ablation)Smoothed online SGD · Single-index models with information exponent k*sample complexity: d^{k^\star-1} -> d^{k^\star/2}Improved
Smooth the loss landscapeOnline SGD for single-index models · Initialization region, α ≲ λ d^{-1/2}gradient signal-to-noise ratioImproved

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