paper-with-me

홈 › Papers

Efficient Full-Matrix Adaptive Regularization

2018-06-08 · ICLR 2019 5 · Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang

Adaptive regularization methods pre-multiply a descent direction by a preconditioning matrix. Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive. We show how to modify full-matrix adaptive regularization in order to make it practical and effective. We also provide a novel theoretical analysis for adaptive regularization in non-convex optimization settings. The core of our algorithm, termed GGT, consists of the efficient computation of the inverse square root of a low-rank matrix. Our preliminary experiments show improved iteration-wise convergence rates across synthetic tasks and standard deep learning benchmarks, and that the more carefully-preconditioned steps sometimes lead to a better solution.

📄 PDF Abstract BibTeX arXiv:1806.02958

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method

2016-09-12 · Nishant A. Mehta, Alistair Rendell, Anish Varghese, Christfried Webers

The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. T…

Adaptive and Implicit Regularization for Matrix Completion

2022-08-11 · Zhemin Li, Tao Sun, Hongxia Wang, Bao Wang

The explicit low-rank regularization, e.g., nuclear norm regularization, has been widely used in imaging sciences. However, it has been found that implicit regularization outperforms explicit ones in various image proces…

Matrix Completion

AIR-Net: Adaptive and Implicit Regularization Neural Network for Matrix Completion

2021-10-12 · Zhemin Li, Tao Sun, Hongxia Wang, Bao Wang

The explicit low-rank regularization, e.g., nuclear norm regularization, has been widely used in imaging sciences. However, it has been found that implicit regularization outperforms explicit ones in various image proces…

Matrix CompletionMissing Elements

Bayesian Matrix Completion via Adaptive Relaxed Spectral Regularization

2015-12-03 · Yang Song, Jun Zhu

Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results. However, little work has been done on Bayesian matrix completion based on the more direct spectral …

Bayesian InferenceCollaborative FilteringMatrix Completion

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

2023-02-07 · NeurIPS 2023 11

Adaptive regularization methods that exploit more than the diagonal entries exhibit state of the art performance for many tasks, but can be prohibitive in terms of memory and running time. We find the spectra of the Kron…