Truncated Newton methods, also known as Hessian-free optimization, are a family of optimization algorithms designed for optimizing non-linear… (More)

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

2017

2017

- Ludovic Métivier, R. Brossier, +5 authors Stéphane Operto
- 2017

Full Waveform Inversion (FWI) is a promising seismic imaging method. It aims at computing quantitative estimates of the… (More)

Is this relevant?

Highly Cited

2015

Highly Cited

2015

- James Martens, Roger B. Grosse
- ICML
- 2015

We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-factored… (More)

Is this relevant?

2014

2014

- Ladislav Luksan, Jan Vlcek
- Applied Mathematics and Computation
- 2014

In this paper, we study an efficient tridiagonal preconditioner, based on numerical differentiation, applied to the matrix-free… (More)

Is this relevant?

2013

2013

- Ludovic Métivier, R. Brossier, Stéphane Operto, Jean Virieux
- SIAM Review
- 2013

Full Waveform Inversion (FWI) is a powerful method for reconstructing subsurface parameters from local measurements of the… (More)

Is this relevant?

2013

2013

Full Waveform Inversion (FWI) methods use generally gradient based method, such as the nonlinear conjugate gradient method or… (More)

Is this relevant?

Highly Cited

2011

Highly Cited

2011

- Ilya Sutskever, James Martens, Geoffrey E. Hinton
- ICML
- 2011

Recurrent Neural Networks (RNNs) are very powerful sequence models that do not enjoy widespread use because it is extremely… (More)

Is this relevant?

Review

2010

Review

2010

This report is devoted to preconditioning techniques for the matrix-free truncated Newton method. After a review of basic known… (More)

Is this relevant?

2009

2009

- Danny Bickson, Danny Dolev
- 2009

We propose a new distributed algorithm for computing a truncated Newton method, where the main diagonal of the Hessian is… (More)

Is this relevant?

2005

2005

- Massimo Roma
- Optimization Methods and Software
- 2005

This paper deals with the preconditioning of truncated Newton methods for the solution of large scale nonlinear unconstrained… (More)

Is this relevant?

1999

1999

- C. T. KELLEYy, E. W. SACHSz, Ezekiel Sachs
- 1999

We consider unconstrained minimization problems that have functions and gradients given by “black box” codes with error control… (More)

Is this relevant?