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

4 results for “spectrum-preserving”

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformationcs.LG

Pion optimizes LLMs by preserving weight matrix singular values.

problem Training large language models (LLMs) with standard optimizers leads to unstable weight matrices.

method Pion uses orthogonal transformations to update weight matrices, preserving their singular values.

result Pion offers a stable alternative to standard optimizers for LLM pretraining and finetuning.

optimization large language models singular values orthogonal transformations stability

2026-05-12abs ↗pdf ↗

A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarseningcs.LG

This study improves graph coarsening methods by preserving graph spectrum and distances.

problem Solving large-scale graph problems by working on a smaller graph.

method Developed a geometric approach using Gromov--Wasserstein distance to minimize the difference between graph distances and their coarsened versions.

result Minimizing the difference between graph distances and their coarsened versions can be achieved using the weighted kernel

K

-means method.

graph coarsening Gromov--Wasserstein distance spectrum-preserving graph classification graph regression

2023-06-15abs ↗pdf ↗

Towards Scalable Spectral Clustering via Spectrum-Preserving Sparsificationcs.LG

The eigendeomposition of nearest-neighbor (NN) graph Laplacian matrices is the main computational bottleneck in spectral clustering. In this work, we introduce a highly-scalable, spectrum-preserving graph sparsification algorithm that enables to build ultra-sparse NN (u-NN) graphs with guaranteed preservation of the or…

2017-10-12abs ↗pdf ↗

Accelerate Support Vector Clustering via Spectrum-Preserving Data Compressioncs.LG

This paper speeds up SVC clustering by compressing data while preserving key properties.

problem Efficiently clustering large-scale real-world data sets.

method Spectrum-preserving data compression for fast support vector clustering.

result Achieved 100X and 115X speedups on real-world data sets while maintaining clustering quality.

Support Vector Clustering Data Compression Spectral Methods Clustering Speedup Real-World Data

2023-04-19abs ↗pdf ↗