On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Norm-Normalization”

FedNNNN: Norm-Normalized Neural Network Aggregation for Fast and Accurate Federated Learningcs.LG

FedNNNN improves FL by adjusting model update vector norms.

problem Slow convergence and low prediction accuracy in FL.

method Norm-Normalized Neural Network Aggregation (FedNNNN) with momentum control.

result Up to 5.4% accuracy improvement on multiple datasets.

Federated Learning Aggregation Techniques Norm-Normalization Momentum Control Prediction Accuracy

2020-08-11abs ↗pdf ↗

Geometric Approaches to Matrix Normalization and Graph Balancingmath.DG

The paper studies matrix normalization and graph balancing using a new functional and gradient descent.

problem Matrix normalization and graph balancing.

method A new functional called the non-normal energy, and gradient descent.

result Gradient descent of the non-normal energy converges to balanced graphs and preserves spectra and realness of weights.

matrix normalization graph balancing gradient descent non-normal energy symplectic geometry

2024-05-10abs ↗pdf ↗

Instance-Level Meta Normalizationcs.LG

This paper presents a normalization mechanism called Instance-Level Meta Normalization (ILM~Norm) to address a learning-to-normalize problem. ILM~Norm learns to predict the normalization parameters via both the feature feed-forward and the gradient back-propagation paths. ILM~Norm provides a meta normalization mechanis…

2019-04-06abs ↗pdf ↗

Slope norm and an algorithm to compute the crosscap numbermath.GT

New algorithms compute crosscap numbers of knots and 3-manifolds.

problem Computing crosscap numbers for knots and 3-manifolds.

method 0-efficient triangulations and normal surface theory.

result Determine crosscap numbers for knots and 3-manifolds.

crosscap number knot theory 3-manifolds slope norm normal surfaces

2021-08-17abs ↗pdf ↗

What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learningcs.LG

FF algorithm uses goodness as a likelihood-ratio test for scalar normalization.

problem Training each layer locally with scalar goodness.

method FF algorithm uses a likelihood-ratio test with squared goodness as the sufficient statistic.

result The FF algorithm generalizes to anisotropic and heavy-tailed populations.

Forward-Forward algorithm scalar goodness likelihood-ratio sufficient statistic Mahalanobis goodness

2026-07-14abs ↗pdf ↗

What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learningcs.LG

FF algorithm uses goodness as a measure of input quality, derived from likelihood-ratio tests.

problem Training each layer locally with a goodness measure.

method FF algorithm uses a likelihood-ratio test to define goodness, which is the sum of squared activations normalized between layers.

result The goodness measure is a sufficient statistic for a likelihood-ratio test, explaining the FF algorithm's performance.

Forward-Forward algorithm likelihood-ratio goodness measure scalar goodness squared activations

2026-07-14abs ↗pdf ↗