paper-with-me

홈 › Papers

SGD with a Constant Large Learning Rate Can Converge to Local Maxima

2021-07-25 · Liu Ziyin, Botao Li, James B. Simon, Masahito Ueda

Previous works on stochastic gradient descent (SGD) often focus on its success. In this work, we construct worst-case optimization problems illustrating that, when not in the regimes that the previous works often assume, SGD can exhibit many strange and potentially undesirable behaviors. Specifically, we construct landscapes and data distributions such that (1) SGD converges to local maxima, (2) SGD escapes saddle points arbitrarily slowly, (3) SGD prefers sharp minima over flat ones, and (4) AMSGrad converges to local maxima. We also realize results in a minimal neural network-like example. Our results highlight the importance of simultaneously analyzing the minibatch sampling, discrete-time updates rules, and realistic landscapes to understand the role of SGD in deep learning.

📄 PDF Abstract BibTeX arXiv:2107.11774

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
AMSGrad AMSGrad is a stochastic optimization method that seeks to fix a convergence issue with Adam based optimizers. AMSGrad uses the…

Similar Papers 제목 키워드 기반

Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution

2023-09-29 · Kenneth Allen, Ming-Jun Lai, Zhaiming Shen

We study the classic matrix cross approximation based on the maximal volume submatrices. Our main results consist of an improvement of the classic estimate for matrix cross approximation and a greedy approach for finding…

Computational EfficiencyImage Compression

SGD Can Converge to Local Maxima

2021-09-29 · ICLR 2022 4 · Liu Ziyin, Botao Li, James B Simon, Masahito Ueda

Stochastic gradient descent (SGD) is widely used for the nonlinear, nonconvex problem of training deep neural networks, but its behavior remains poorly understood. Many theoretical works have studied SGD, but they common…

Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences

2016-09-04 · NeurIPS 2016 12 · Chi Jin, Yuchen Zhang, Sivaraman Balakrishnan, Martin J. Wainwright 외

We provide two fundamental results on the population (infinite-sample) likelihood function of Gaussian mixture models with $M \geq 3$ components. Our first main result shows that the population likelihood function has ba…

Open-Ended Question Answering

On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

2018-07-11 · Hoang Thanh-Tung, Truyen Tran

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual lear…

Continual Learning

Improved Convergence Guarantees for Learning Gaussian Mixture Models by EM and Gradient EM

2021-01-03 · Nimrod Segol, Boaz Nadler

We consider the problem of estimating the parameters a Gaussian Mixture Model with K components of known weights, all with an identity covariance matrix. We make two contributions. First, at the population level, we pres…