paper-with-me

Papers

Nystrom Method for Accurate and Scalable Implicit Differentiation

2023-02-20 · Ryuichiro Hataya, Makoto Yamada

The essential difficulty of gradient-based bilevel optimization using implicit differentiation is to estimate the inverse Hessian vector product with respect to neural network parameters. This paper proposes to tackle this problem by the Nystrom method and the Woodbury matrix identity, exploiting the low-rankness of the Hessian. Compared to existing methods using iterative approximation, such as conjugate gradient and the Neumann series approximation, the proposed method avoids numerical instability and can be efficiently computed in matrix operations without iterations. As a result, the proposed method works stably in various tasks and is faster than iterative approximations. Throughout experiments including large-scale hyperparameter optimization and meta learning, we demonstrate that the Nystrom method consistently achieves comparable or even superior performance to other approaches. The source code is available from https://github.com/moskomule/hypergrad.

📄 PDF Abstract BibTeX arXiv:2302.09726

Code (4)

moskomule/hypergrad 공식 구현 pytorch
MindSpore-scientific-2/code-4/tree/main/nystrom-attention mindspore
MindSpore-scientific-2/code-5/tree/main/nystrom-attention mindspore
aai-institute/pyDVL pytorch

Tasks

Bilevel OptimizationHyperparameter OptimizationMeta-Learning

Similar Papers 제목 키워드 기반

Recursive Sampling for the Nystrom Method

2017-12-01 · NeurIPS 2017 12 · Cameron Musco, Christopher Musco

We give the first algorithm for kernel Nystrom approximation that runs in linear time in the number of training points and is provably accurate for all kernel matrices, without dependence on regularity or incoherence con…

Spectral Clustering using Eigenspectrum Shape Based Nystrom Sampling

2020-07-21 · Djallel Bouneffouf

Spectral clustering has shown a superior performance in analyzing the cluster structure. However, its computational complexity limits its application in analyzing large-scale data. To address this problem, many low-rank …

Clustering

Improved Fixed-Rank Nyström Approximation via QR Decomposition: Practical and Theoretical Aspects

2017-08-08 · Farhad Pourkamali-Anaraki, Stephen Becker

The Nystrom method is a popular technique that uses a small number of landmark points to compute a fixed-rank approximation of large kernel matrices that arise in machine learning problems. In practice, to ensure high qu…

Ensemble Nystrom Method

2009-12-01 · NeurIPS 2009 12 · Sanjiv Kumar, Mehryar Mohri, Ameet Talwalkar

A crucial technique for scaling kernel methods to very large data sets reaching or exceeding millions of instances is based on low-rank approximation of kernel matrices. We introduce a new family of algorithms based on m…

regression

Randomized Clustered Nystrom for Large-Scale Kernel Machines

2016-12-20 · Farhad Pourkamali-Anaraki, Stephen Becker

The Nystrom method has been popular for generating the low-rank approximation of kernel matrices that arise in many machine learning problems. The approximation quality of the Nystrom method depends crucially on the numb…

Clustering