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.
On account of its many successes in inference tasks and denoising applications, Dictionary Learning (DL) and its related sparse optimization problems have garnered a lot of research interest. While most solutions have focused on single layer dictionaries, the improved recently proposed Deep DL (DDL) methods have also f…
Improves GANs by sampling from an energy-based model induced by discriminator scores.
This paper introduces a new method for model selection and more generally hyperparameter selection in machine learning. Minimum description length (MDL) is an established method for model selection, which is however not directly aimed at minimizing generalization error, which is often the primary goal in machine learni…
Framework integrates brain connectivity data for clinical predictions.
We propose denoising dictionary learning (DDL), a simple yet effective technique as a protection measure against adversarial perturbations. We examined denoising dictionary learning on MNIST and CIFAR10 perturbed under two different perturbation techniques, fast gradient sign (FGSM) and jacobian saliency maps (JSMA). W…
DWTS uses observational data to improve clinical trial efficiency.
Deep model integrates MRI and DTI for autism severity prediction.
Improves deep generative model samples via gradient flow.