AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Parallel Deep Neural Networks Have Zero Duality Gap

Yifei Wang, Tolga Ergen, Mert Pilanci

ICLR 2023 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 1 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 parallel branches with L-th power Frobenius regularization instead of standard architecture with weight decay (deep linear)deep linear networks, L>=3 · theoretical analysis, vector-output linear networksduality gap (P vs D)Improved
Stacking standard deep ReLU networks in parallel with modified regularization (sufficient branches)deep ReLU networks, arbitrary depth · theoretical analysisduality gap (P vs D)Improved
Standard deep linear network with L>=3 (no parallel branches)standard deep linear networks · theoretical analysisduality gap (P vs D)Hurt
Weight decay (l2 regularization) on standard deep linear networksstandard deep linear networks · theoretical analysissolution rankNo clear effect
Rank-1 data matrix for three-layer scalar-output standard ReLU networkthree-layer standard ReLU networks · theoretical analysisduality gap (P vs D)Improved

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