Search Results for author: Ching-pei Lee

Found 9 papers, 4 papers with code

Escaping Spurious Local Minima of Low-Rank Matrix Factorization Through Convex Lifting

no code implementations29 Apr 2022 Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh

This work proposes a rapid global solver for nonconvex low-rank matrix factorization (MF) problems that we name MF-Global.

Training Structured Neural Networks Through Manifold Identification and Variance Reduction

1 code implementation ICLR 2022 Zih-Syuan Huang, Ching-pei Lee

This paper proposes an algorithm (RMDA) for training neural networks (NNs) with a regularization term for promoting desired structures.

Data Augmentation

Momentum as Variance-Reduced Stochastic Gradient

no code implementations29 Sep 2021 Zih-Syuan Huang, Ching-pei Lee

Stochastic gradient descent with momentum (SGD+M) is widely used to empirically improve the convergence behavior and the generalization performance of plain stochastic gradient descent (SGD) in the training of deep learning models, but our theoretical understanding for SGD+M is still very limited.

Data Augmentation

Accelerating Inexact Successive Quadratic Approximation for Regularized Optimization Through Manifold Identification

no code implementations4 Dec 2020 Ching-pei Lee

We show that for a wide class of degenerate solutions, ISQA+ possesses superlinear convergence not just only in iterations, but also in running time because the cost per iteration is bounded.

Optimization and Control

A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization

1 code implementation12 Dec 2019 Ching-pei Lee, Cong Han Lim, Stephen J. Wright

When applied to the distributed dual ERM problem, unlike state of the art that takes only the block-diagonal part of the Hessian, our approach is able to utilize global curvature information and is thus magnitudes faster.

Distributed Optimization

A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization

1 code implementation4 Mar 2018 Ching-pei Lee, Cong Han Lim, Stephen J. Wright

Initial computational results on convex problems demonstrate that our method significantly improves on communication cost and running time over the current state-of-the-art methods.

Distributed Optimization

On the Equivalence of CoCoA+ and DisDCA

no code implementations13 Jun 2015 Ching-pei Lee

In this document, we show that the algorithm CoCoA+ (Ma et al., ICML, 2015) under the setting used in their experiments, which is also the best setting suggested by the authors that proposed this algorithm, is equivalent to the practical variant of DisDCA (Yang, NIPS, 2013).

Cannot find the paper you are looking for? You can Submit a new open access paper.