paper-with-me

홈 › Papers

Momentum-inspired Low-Rank Coordinate Descent for Diagonally Constrained SDPs

2021-06-16 · Junhyung Lyle Kim, Jose Antonio Lara Benitez, Mohammad Taha Toghani, Cameron Wolfe, Zhiwei Zhang, Anastasios Kyrillidis

We present a novel, practical, and provable approach for solving diagonally constrained semi-definite programming (SDP) problems at scale using accelerated non-convex programming. Our algorithm non-trivially combines acceleration motions from convex optimization with coordinate power iteration and matrix factorization techniques. The algorithm is extremely simple to implement, and adds only a single extra hyperparameter -- momentum. We prove that our method admits local linear convergence in the neighborhood of the optimum and always converges to a first-order critical point. Experimentally, we showcase the merits of our method on three major application domains: MaxCut, MaxSAT, and MIMO signal detection. In all cases, our methodology provides significant speedups over non-convex and convex SDP solvers -- 5X faster than state-of-the-art non-convex solvers, and 9 to 10^3 X faster than convex SDP solvers -- with comparable or improved solution quality.

📄 PDF Abstract BibTeX arXiv:2106.08775

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Quantifying the Preconditioning Effect of Adam

2024-02-11 · Rudrajit Das, Naman Agarwal, Sujay Sanghavi, Inderjit S. Dhillon

There is a notable dearth of results characterizing the preconditioning effect of Adam and showing how it may alleviate the curse of ill-conditioning -- an issue plaguing gradient descent (GD). In this work, we perform a…

The Loss Does Not See the Basis, but Adam Does

2026-08-05 · Devender Singh hf

Gradient descent on a factored model W = UV^top is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization, is not. We trace the difference to the gauge symmetry of the loss, …

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

2020-02-11 · ICML 2020 1 · Filip Hanzely, Dmitry Kovalev, Peter Richtarik

We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our method can deal with problems that include a …

Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent

2020-05-18 · Tian Tong, Cong Ma, Yuejie Chi

Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science. A popular approach in practice is to factorize the matrix into two compact lo…

Matrix Completion

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

2021-10-18 · Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li 외

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on exces…

BIG-bench Machine Learningimage-classificationImage ClassificationLanguage Modeling+3