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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “doubly-accelerated”

Doubly Accelerated Methods for Faster CCA and Generalized Eigendecompositionmath.OC

New algorithms solve k-GenEV and k-CCA problems faster.

problem Finding top k generalized eigenvectors and canonical-correlation vectors.

method Proposed

\mathtt{LazyEV}

and

\mathtt{LazyCCA}

algorithms with linear dependence on input size and k.

result First doubly-accelerated algorithms with running times independent of matrix condition number and eigengap.

generalized eigenvectors canonical-correlation analysis doubly-accelerated running time matrix condition number

2016-07-20abs ↗pdf ↗

Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimizationmath.OC

New method improves mini-batch efficiency for convex optimization problems.

problem Efficiently solving convex regularized empirical risk minimization with mini-batches.

method Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method with double acceleration and variance reduction.

result Significantly reduces the number of mini-batches needed for optimal performance.

acceleration stochastic gradient variance reduction mini-batches empirical risk minimization

2017-03-01abs ↗pdf ↗