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.

168,738 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “Newton-CG”

A Newton-CG based augmented Lagrangian method for finding a second-order stationary point of nonconvex equality constrained optimization with complexity guaranteesmath.OC

Paper proposes a new method to find approximate SOSP for nonconvex constrained optimization problems.

problem Finding a second-order stationary point of nonconvex equality constrained optimization.

method Newton-CG based augmented Lagrangian method with a new Newton-CG subproblem solver.

result Achieves better complexity guarantees for finding approximate SOSP with high probability.

Newton-CG augmented Lagrangian second-order stationary point nonconvex optimization equality constraints

2023-01-09abs ↗pdf ↗

A Newton-CG based barrier method for finding a second-order stationary point of nonconvex conic optimization with complexity guaranteesmath.OC

Paper proposes a method to find approximate SOSP for nonconvex conic optimization problems.

problem Finding approximate second-order stationary points in nonconvex conic optimization.

method Newton-CG based barrier method with complexity guarantees.

result Achieves iteration complexity of O(ε^(-3/2)) for finding (ε,√ε)-SOSP.

Newton-CG barrier method second-order stationary point nonconvex optimization conic optimization

2022-07-12abs ↗pdf ↗

A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimizationmath.OC

Paper proposes a method to find approximate SOSP for nonconvex conic optimization problems.

problem Finding approximate second-order stationary points in nonconvex conic optimization.

method Newton-CG based barrier-augmented Lagrangian method.

result Method achieves complexity bounds of

\widetilde{\cal O}(ε^{-11/2})

and

\widetilde{\cal O}(ε^{-11/2}\min\{n,ε^{-5/4}\})

for finding an

(ε,\sqrtε)

-SOSP.

Newton-CG Lagrangian method nonconvex optimization second-order stationary point conic optimization

2023-01-10abs ↗pdf ↗

Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completionstat.ML

The sparse inverse covariance estimation problem is commonly solved using an $\ell_{1}$ -regularized Gaussian maximum likelihood estimator known as "graphical lasso", but its computational cost becomes prohibitive for large data sets. A recent line of results showed--under mild assumptions--that the graphical lasso esti…

2018-02-14abs ↗pdf ↗

Graph-Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometrystat.ML

GS-B $^3$ SE improves label shift estimation by smoothing priors on a graph.

problem Label shift adaptation when source and target distributions share conditional but not marginal probabilities.

method Graph-Smoothed Bayesian Black-Box Shift Estimator (GS-B

^3

SE) places Laplacian-Gaussian priors on log-priors and confusion-matrix columns tied by a label-similarity graph.

result GS-B

^3

SE produces a tractable posterior with HMC or Newton-CG schemes, proving identifiability, contraction, and robustness.

label shift black-box shift estimation graph smoothing information geometry Laplacian-Gaussian priors

2025-05-22abs ↗pdf ↗

Alternating Direction Methods for Latent Variable Gaussian Graphical Model Selectionmath.OC

Chandrasekaran, Parrilo and Willsky (2010) proposed a convex optimization problem to characterize graphical model selection in the presence of unobserved variables. This convex optimization problem aims to estimate an inverse covariance matrix that can be decomposed into a sparse matrix minus a low-rank matrix from sam…

2012-06-06abs ↗pdf ↗

Certifying clusters from sum-of-norms clusteringcs.LG

This paper certifies cluster assignments from sum-of-norms clustering algorithms.

problem Certifying the correct cluster assignments from approximate solutions of sum-of-norms clustering.

method Presented a clustering test that identifies and certifies the correct cluster assignment from an approximate solution.

result The correct cluster assignment is guaranteed to be certified by a primal-dual path following algorithm after sufficient iterations.

sum-of-norms clustering clustering certification convex optimization subgradient descent ADMM

2020-06-19abs ↗pdf ↗

A Retrospective Approximation Approach for Smooth Stochastic Optimizationmath.OC

A new approach RA improves stochastic optimization by executing multiple steps between subsample updates.

problem Improving the efficiency and effectiveness of stochastic optimization methods.

method Developed Retrospective Approximation (RA) which executes multiple steps between subsample updates using a deterministic solver.

result RA achieves almost sure and

L_1

consistency under weak conditions and optimizes iteration and oracle complexity.

stochastic optimization retrospective approximation deterministic solver stochastic gradient smooth objective

2021-03-07abs ↗pdf ↗