AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Dimension-Free Bounds for Low-Precision Training

Zheng Li, Christopher M De Sa

NeurIPS 2019 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 6 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
increase model dimension d from small to largeSGD and LP-SGD (8-bit and 6-bit) · Synthetic linear regressionnoise ball sizeNo clear effect
increase nonzero entries s (changing sigma_1 and L_1) at fixed d=1024LP-SGD vs SGD · Synthetic linear regressionloss gapHurt
assign exponent bits per Theorem 5 (5 of 20 total bits)LP-SGD with normal FPQ · Synthetic linear regressionnoise ball sizeImproved
vary exponent bits in 16-bit floating point formatsLP-SGD · MNISTloss gapImproved

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