Skip to search formSkip to main contentSkip to account menuSemantic Scholar Semantic Scholar's Logo Search 205,704,947 papers from all fields of science

Search

Semantic Scholar uses AI to extract papers important to this topic.

Highly Cited

2019

Highly Cited

2019

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can…

Highly Cited

2018

Highly Cited

2018

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly…

Review

2016

Review

2016

Gradient descent optimization algorithms, while increasingly popular, are often used as black-box optimizers, as practical…

Highly Cited

2016

Highly Cited

2016

The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this…

Highly Cited

2016

Highly Cited

2016

We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for…

Highly Cited

2009

Highly Cited

2009

We consider the problem of minimizing the sum of a smooth function and a separable convex function. This problem includes as…

Highly Cited

2005

Highly Cited

2005

We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function…

Highly Cited

2005

Highly Cited

2005

We study a general online convex optimization problem. We have a convex set <i>S</i> and an unknown sequence of cost functions <i…

Highly Cited

1999

Highly Cited

1999

We provide an abstract characterization of boosting algorithms as gradient decsent on cost-functionals in an inner-product…

Highly Cited

1997

Highly Cited

1997

We consider two algorithm for on-line prediction based on a linear model. The algorithms are the well-known Gradient Descent (GD…