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.

168,982 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · May 202019922001200920172026
2 results for “gradient-sparse”
Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurementsstat.ML

Algorithm estimates sparse signals from linear measurements, improving recovery guarantees.

problem Estimating gradient-sparse signals from noisy linear measurements.
method Iterative alpha expansion with proximal descent and geometric penalty decay.
result Global recovery guarantees under cut-restricted isometry property for Gaussian designs.
sparse signalsgradient-sparsecompressed sensingiterative algorithmproximal descent
2019-05-15abs ↗pdf ↗
Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphsstat.ML

A new algorithm estimates sparse gradients on graphs with improved risk bounds.

problem Estimating sparse gradients on graph-structured data.
method Tree-Projected Gradient Descent algorithm for gradient-sparse parameters.
result Achieves risk bound of s∗nlog⁡(1+ps∗)\frac{s^*}{n} \log (1+\frac{p}{s^*}).
gradient descentsparse parametersgraph-structured datatree projectionconvex optimization
2020-05-31abs ↗pdf ↗