Research
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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Oct 201919922001200920172026
3 results for “log-domain”
Neural Network Training with Approximate Logarithmic Computationscs.LG

Paper proposes a log-domain training method to reduce neural network complexity.

problem High computational complexity in training deep neural networks limits real-time training.
method End-to-end training and inference scheme using approximate logarithmic operations in the log-domain.
result 16-bit log-based training achieves within 1% accuracy of floating-point baselines.
neural networkslog-domainapproximate computationtraining complexityreal-time
2019-10-22abs ↗pdf ↗
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptivecs.LG

Diffusion models adapt to data geometry through log-domain smoothing.

problem Understanding why diffusion models generalize well across diverse domains.
method Investigating the role of score matching and log-domain smoothing in diffusion models.
result Log-domain smoothing adapts the diffusion model to the data manifold.
diffusion modelsscore matchinglog-domain smoothingmanifold hypothesisgeneralization
2025-10-02abs ↗pdf ↗