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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “curvature-aided”

SUCAG: Stochastic Unbiased Curvature-aided Gradient Method for Distributed Optimizationmath.OC

SUCAG accelerates convergence in distributed optimization with unbiased curvature information.

problem Efficiently solving finite sum optimization problems in distributed settings.

method Stochastic Unbiased Curvature-aided Gradient (SUCAG) method using Hessian information.

result Establishes linear convergence for strongly convex problems under asynchronous model.

distributed optimization stochastic gradient curvature-aided asynchronous linear convergence

2018-03-22abs ↗pdf ↗

Accelerating Incremental Gradient Optimization with Curvature Informationmath.OC

New method accelerates gradient optimization using curvature information.

problem Solving large-scale learning optimization problems efficiently.

method Curvature-aided gradient tracking step for incremental gradient optimization.

result Proves linear convergence rates for new methods.

optimization gradient methods curvature acceleration finite sum

2018-05-31abs ↗pdf ↗

Curvature-aided Incremental Aggregated Gradient Methodstat.ML

CIAG method accelerates optimization for high-dimensional problems.

problem Training classifiers for high-dimensional problems with large datasets.

method CIAG method uses curvature information to accelerate IAG methods.

result Improved linear convergence rate over state-of-the-art IAG methods.

optimization finite sum curvature aggregated gradient Hessian

2017-10-24abs ↗pdf ↗

On the Convex Behavior of Deep Neural Networks in Relation to the Layers' Widthcs.LG

Wider neural networks have predominantly positive curvature, aiding optimization.

problem Understanding the convex behavior of deep neural networks with varying layer widths.

method Hessian decomposition and gradient analysis of over-parameterized networks.

result For wide networks, the Hessian is dominated by the positive component G, leading to positive curvature.

neural networks convex optimization over-parameterization gradient descent Hessian

2020-01-14abs ↗pdf ↗