The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
Abstract
We propose a generic method for iteratively approximating various second-order gradient steps—-Newton, Gauss-Newton, Levenberg-Marquardt, and natural gradient—-in linear time per iteration, using special curvature matrix-vector products that can be computed in O(n). Two recent acceleration techniques for on-line learning, matrix momentum and stochastic meta-descent (SMD), implement this approach. Since both were originally derived by very different routes, this offers fresh insight into their operation, resulting in further improvements to SMD.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
An Algorithm for Least-Squares Estimation of Nonlinear Parameters
Marquardt, D. W. (1963) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0111030 · Cited by 30,728
Neural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
A method for the solution of certain non-linear problems in least squares
Levenberg, K. (1944) · Quarterly of Applied Mathematics · doi:10.1090/qam/10666 · Cited by 12,359
Natural Gradient Works Efficiently in Learning
Amari, S.-I. (1998) · Neural Computation · doi:10.1162/089976698300017746 · Cited by 2,681
Differential-Geometrical Methods in Statistics
Amari, S.-I. (1985) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-5056-2 · Cited by 1,673 · cited 2×
“The Fisher information matrix proper, F̄ ≡ 〈F〉E x, describes the geometric structure of weight space (Amari, 1985) and is used in the natural gradient descent approach (Amari, 1998).”
BackgroundMethodNumerical recipes in C (2nd ed.): the art of scientific computing
Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1992) · Cambridge University Press eBooks · Cited by 1,156
Fast Exact Multiplication by the Hessian
Pearlmutter, B. A. (1994) · Neural Computation · doi:10.1162/neco.1994.6.1.147 · Cited by 540
Training Multilayer Perceptrons with the Extended Kalman Algorithm
Singhal, S., & Wu, L. (1988) · neural information processing systems · Cited by 320
BACKPROPAGATION: PAST AND FUTURE
Werbos, P. J. (1988) · Cited by 224
Additive versus exponentiated gradient updates for linear prediction
Kivinen, J., & Warmuth, M. K. (1995) · Proceedings of the twenty-seventh annual ACM symposium on Theory of computing - STOC '95 · doi:10.1145/225058.225121 · Cited by 223
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
A survey on deep learning and its applications
Dong, S., Wang, P., & Abbas, K. (2021) · Computer Science Review · doi:10.1016/j.cosrev.2021.100379 · Cited by 1,800
Framewise phoneme classification with bidirectional LSTM networks
Graves, A., & Schmidhuber, J. (2006) · Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. · doi:10.1109/ijcnn.2005.1556215 · Cited by 618
Audio-visual speech recognition using deep learning
Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H. G., & Ogata, T. (2015) · Applied Intelligence · doi:10.1007/s10489-014-0629-7 · Cited by 579
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Wu, Y., Mansimov, E., Liao, S., Grosse, R., & Ba, J. L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.05144 · Cited by 432
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Martens, J., & Grosse, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.05671 · Cited by 414
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
Zhuang, J., Tang, T., Ding, Y., Tatikonda, S., Dvornek, N., Papademetris, X., & Duncan, J. S. (2020) · arXiv · doi:10.48550/arxiv.2010.07468 · Cited by 382
Neural Optimizer Search with Reinforcement Learning
Bello, I., Zoph, B., Vasudevan, V., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1709.07417 · Cited by 319
Accelerated training of conditional random fields with stochastic gradient methods
Vishwanathan, S. V. N., Schraudolph, N. N., Schmidt, M. W., & Murphy, K. P. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143966 · Cited by 278
Self-citationSchaul, T., Zhang, S., & LeCun, Y. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.1106 · Cited by 266
(2015) · arXiv (Cornell University) · Cited by 182
Metadata
- Authors
- Schraudolph, N. N.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2002-07-01
- Volume
- 14
- Issue
- 7
- Pages
- 1723-1738
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2130984546
- Cited by
- 265
- References
- 18
- FWCI
- 4.01
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.