paper-with-me

Papers

Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for $k$-means Clustering

2017-10-21 · Penghang Yin, Minh Pham, Adam Oberman, Stanley Osher

In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample a mini-batch gradient in every iteration. It is the average of the fixed-point trajectory that is carried over to the next gradient step. We draw connections between the proposed stochastic backward Euler and the recent entropy stochastic gradient descent (Entropy-SGD) for improving the training of deep neural networks. Numerical experiments on various synthetic and real datasets show that the proposed algorithm provides better clustering results compared to $k$-means algorithms in the sense that it decreased the objective function (the cluster) and is much more robust to initialization.

📄 PDF Abstract BibTeX arXiv:1710.07746

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equations

2020-10-03 · Lorenc Kapllani, Long Teng

In this work, we propose a new deep learning-based scheme for solving high dimensional nonlinear backward stochastic differential equations (BSDEs). The idea is to reformulate the problem as a global optimization, where …

global-optimization

Implicit biases in multitask and continual learning from a backward error analysis perspective

2023-11-01 · Benoit Dherin

Using backward error analysis, we compute implicit training biases in multitask and continual learning settings for neural networks trained with stochastic gradient descent. In particular, we derive modified losses that …

Continual Learning

The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks

2025-02-08 · Sholom Schechtman, Nicolas Schreuder

We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large class of deep neural networks with ReLU-type…

Binary Classification

Implicit Gradient Regularization

2020-09-23 · ICLR 2021 1 · David G. T. Barrett, Benoit Dherin

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by pe…

Implicit regularisation in stochastic gradient descent: from single-objective to two-player games

2023-07-11 · Mihaela Rosca, Marc Peter Deisenroth

Recent years have seen many insights on deep learning optimisation being brought forward by finding implicit regularisation effects of commonly used gradient-based optimisers. Understanding implicit regularisation can no…