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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Semi-smoothness”

Improved dimension dependence of a proximal algorithm for samplingmath.ST

Improved sampling algorithm with state-of-the-art complexity bounds.

problem Efficient sampling from various probability distributions.

method Proximal sampler with inexact restricted Gaussian oracle.

result State-of-the-art complexity bounds in almost all settings.

sampling algorithms proximal sampler rejection sampling semi-smooth functions Gaussian distributions

2023-02-20abs ↗pdf ↗

An Efficient Semi-smooth Newton Augmented Lagrangian Method for Elastic Netstat.ML

Efficiently solves Elastic Net in high dimensions with Newton method.

problem Feature selection in high-dimensional data with non-negligible collinearity.

method Semi-smooth Newton Augmented Lagrangian Method.

result Significantly reduces computational cost compared to competitors.

Elastic Net Feature Selection Newton Method Augmented Lagrangian High Dimensional Data

2020-06-06abs ↗pdf ↗

A Convergence Theory for Federated Average: Beyond Smoothnesscs.LG

This paper analyzes the convergence of Federated Average under relaxed assumptions.

problem Lack of theoretical analysis for Federated Average under assumptions beyond smoothness.

method Relaxing assumptions of strong smoothness to semi-smoothness and semi-Lipschitz properties, and introducing a bound on the gradient.

result Provides a theoretical convergence study on Federated Learning under new assumptions.

Federated Learning Federated Average Convergence Theory Semi-smoothness Semi-Lipschitz

2022-11-03abs ↗pdf ↗

Samplet basis pursuit: Multiresolution scattered data approximation with sparsity constraintsstat.ML

This paper approximates scattered data using samplet coordinates with sparsity constraints.

problem Scattered data approximation with sparsity constraints.

method Samplet basis pursuit with

\ell_1

-regularization, multiresolution techniques, and semi-smooth Newton method.

result The proposed method provides faster convergence and better signal sparsity compared to existing methods.

scattered data samplet basis sparsity constraints multiresolution semi-smooth Newton method

2023-06-16abs ↗pdf ↗

A Convergence Theory for Deep Learning via Over-Parameterizationcs.LG

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural networks with one hidden layer. The theory of multi-layer networks remains largely …

2018-11-09abs ↗pdf ↗

Multi-task Learning for Gaussian Graphical Regressions with High Dimensional Covariatesstat.ME

A new multi-task learning estimator improves Gaussian graphical regression model fitting.

problem High error rate in fitting Gaussian graphical regression models due to separate node-wise lasso regressions.

method Proposes a multi-task learning estimator with cross-task group sparsity and within-task element-wise sparsity penalties, solved via an efficient augmented Lagrangian algorithm.

result Error rate improvement over separate node-wise lasso estimates, demonstrated through simulations and application to gene co-expression network study.

Gaussian graphical regression multi-task learning group sparsity element-wise sparsity augmented Lagrangian

2022-05-21abs ↗pdf ↗