AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Lifted Bregman Training of Neural Networks

Xiaoyu Wang, Martin Benning

JMLR 2023 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 3 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 lifted Bregman loss instead of classical quadratic-penalty lifted training4-layer MLP · MNIST (test)accuracy: 86.3% -> 96.8%Improved
use lifted Bregman loss instead of classical quadratic-penalty lifted training4-layer MLP · Fashion-MNIST (test)accuracy: 80.0% -> 85.7%Improved
train with lifted Bregman instead of SGD with back-propagation4-layer MLP · MNIST (test)accuracy: 96.9% vs 96.8%No clear effect
train with lifted Bregman instead of SGD with back-propagation4-layer MLP · Fashion-MNIST (test)accuracy: 87.9% -> 85.7%Hurt
replace quadratic penalty with Bregman penaltyLifted network · MNIST hidden layerspercentage of linear nodes: 99.9% -> 47.4%, 82.2%, 70.1%Improved
use lifted Bregman instead of GD/SGD with back-propagationSparse autoencoder · MNIST-1Ktraining objective valueImproved
use stochastic variant instead of deterministicLBN-D / GD-BP · MNIST-1K sparse autoencoderconvergence speedImproved
use lifted Bregman instead of GD/SGD with back-propagationSparse autoencoder · MNIST-1Kvalidation lossMixed
use lifted Bregman instead of GD/SGD with back-propagationSparse autoencoder · MNIST-1Kreconstruction qualityImproved
use lifted Bregman instead of GD/SGD with back-propagationSparse autoencoder · MNIST-1Ksparsity stabilityImproved

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