AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Training Linear Neural Networks: Non-Local Convergence and Complexity Results

Armin Eftekhari

ICML 2020 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 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
Restrict gradient flow initialization to the stable set N_{N,alpha} (balanced init, end-to-end product positively correlated with target and bounded away from zero)gradient flow for deep linear networks with one width-1 layer · Theoretical (whitened data, r=1, Assumption 3.6)convergence to global minimizerImproved
Increase network depth N in linear network trained by gradient flowfaraway (non-local) convergence rate of gradient flow · Theoretical bound (Theorem 4.4) and numerical example (Figure 1, dx=5, dy=1, m=50)distance to target / convergence rateImproved
Increase network depth N in linear network trained by gradient flownearby (local) convergence rate of gradient flow · Theoretical bound (Theorem 4.4)convergence rateNo clear effect
Use a balanced (rather than unbalanced) initialization for gradient flowgradient flow on linear networks · Theoretical (Section 3)guarantee of avoiding rank-degenerate limit pointsImproved

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