paper-with-me

Papers

Continuation Path with Linear Convergence Rate

2021-12-09 · Eugene Ndiaye, Ichiro Takeuchi

Path-following algorithms are frequently used in composite optimization problems where a series of subproblems, with varying regularization hyperparameters, are solved sequentially. By reusing the previous solutions as initialization, better convergence speeds have been observed numerically. This makes it a rather useful heuristic to speed up the execution of optimization algorithms in machine learning. We present a primal dual analysis of the path-following algorithm and explore how to design its hyperparameters as well as determining how accurately each subproblem should be solved to guarantee a linear convergence rate on a target problem. Furthermore, considering optimization with a sparsity-inducing penalty, we analyze the change of the active sets with respect to the regularization parameter. The latter can then be adaptively calibrated to finely determine the number of features that will be selected along the solution path. This leads to simple heuristics for calibrating hyperparameters of active set approaches to reduce their complexity and improve their execution time.

📄 PDF Abstract BibTeX arXiv:2112.05104

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Iteratively reweighted penalty alternating minimization methods with continuation for image deblurring

2019-02-09 · Tao Sun, Dongsheng Li, Hao Jiang, Zhe Quan

In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing. We solve this problem by the penalty method and propose the iteratively reweighted al…

DeblurringImage Deblurring

DynaNewton - Accelerating Newton's Method for Machine Learning

2016-05-20 · Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann

Newton's method is a fundamental technique in optimization with quadratic convergence within a neighborhood around the optimum. However reaching this neighborhood is often slow and dominates the computational costs. We e…

BIG-bench Machine Learning

Dynamic Policy Learning for Legged Robot with Simplified Model Pretraining and Model-Homotopy-Inspired Transfer

2025-12-31 · Dongyun Kang, Min-Gyu Kim, Tae-Gyu Song, Hajun Kim 외 arxiv

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires …

Reinforcement Learning

A Primal Dual Active Set with Continuation Algorithm for the \ell^0-Regularized Optimization Problem

2014-03-03 · Yuling Jiao, Bangti Jin, Xiliang Lu

We develop a primal dual active set with continuation algorithm for solving the \ell^0-regularized least-squares problem that frequently arises in compressed sensing. The algorithm couples the the primal dual active set …

compressed sensing

Fixed Points of Belief Propagation -- An Analysis via Polynomial Homotopy Continuation

2016-05-20 · Christian Knoll, Franz Pernkopf, Dhagash Mehta, Tianran Chen

Belief propagation (BP) is an iterative method to perform approximate inference on arbitrary graphical models. Whether BP converges and if the solution is a unique fixed point depends on both the structure and the parame…