The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Flat Minima
Abstract
We present a new algorithm for finding low-complexity neural networks with high generalization capability. The algorithm searches for a “flat” minimum of the error function. A flat minimum is a large connected region in weight space where the error remains approximately constant. An MDL-based, Bayesian argument suggests that flat minima correspond to “simple” networks and low expected overfitting. The argument is based on a Gibbs algorithm variant and a novel way of splitting generalization error into underfitting and overfitting error. Unlike many previous approaches, ours does not require gaussian assumptions and does not depend on a “good” weight prior. Instead we have a prior over input output functions, thus taking into account net architecture and training set. Although our algorithm requires the computation of second-order derivatives, it has backpropagation's order of complexity. Automatically, it effectively prunes units, weights, and input lines. Various experiments with feedforward and recurrent nets are described. In an application to stock market prediction, flat minimum search outperforms conventional backprop, weight decay, and “optimal brain surgeon/optimal brain damage.”
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
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
Cross validatory choice and assessment of statistical predictions
Stone, M. (1974) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1974.tb00994.x · Cited by 10,881
Modeling by shortest data description
Rissanen, J. (1978) · Automatica · doi:10.1016/0005-1098(78)90005-5 · Cited by 6,011
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.415 · Cited by 4,388
Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
Golub, G. H., Heath, M., & Wahba, G. (1979) · Technometrics · doi:10.1080/00401706.1979.10489751 · Cited by 3,934
Hastie, T., & Tibshirani, R. (1986) · Statistical Science · doi:10.1214/ss/1177013604 · Cited by 3,409
Craven, P., & Wahba, G. (1978) · Numerische Mathematik · doi:10.1007/bf01404567 · Cited by 3,388
A practical Bayesian framework for backpropagation networks
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.448 · Cited by 2,917 · cited 4×
“B(w; X 0 )), but it is not obvious how: the \quick and dirty version" (MacKay, 1992a) cannot deal with the unknown constant in B(w; X 0 ).”
BackgroundMethodInfluentialAdvances in Neural Information Processing Systems 37
(2024) · doi:10.52202/079017 · Cited by 2,791
(1993) · CaltechAUTHORS (California Institute of Technology) · Cited by 1,498
Research works printed but not linked: 11
- Buntine W. L., 1991, Complex Systems, 5, 603
- Carter M. J., 1990, Advances in Neural Information Processing Systems, 2, 340
- Fahlman S. E., 1990, Advances in Neural Information Processing Systems 2, D. S. Touretzky, ed., 525
- 10.2307/1268518 · DOI
- Hanson S. J., 1989, Advances in Neural Information Processing Systems 1, D. S. Touretzky, ed., 177
- LeCun Y., 1990, Advances in Neural Information Processing Systems 2, D. S. Touretzky, ed., 598
- Levin A. U., 1994, Advances in Neural Information Processing Systems 6, J. D. Cowan, G. Tesauro, and J. Alspector, eds., 35
- Moody J. E., 1989, Advances in Neural Information Processing Systems 1, D. S. Touretzky, ed., 29
- Mozer M. C., 1989, Advances in Neural Information Processing Systems 1, D. S. Touretzky, ed., 107
- Wang C., 1994, Advances in Neural Information Processing Systems 6, J. D. Cowan, G. Tesauro, and J. Alspector, eds., 303
- Wolpert D. H., 1994, Advances in Neural Information Processing Systems 6, J. D. Cowan, G. Tesauro, and J. Alspector, eds., 200
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
Self-citationPattern Recognition and Neural Networks
Ripley, B. D. (1996) · Cambridge University Press eBooks · doi:10.1017/cbo9780511812651 · Cited by 6,459
Improved Adam Optimizer for Deep Neural Networks
Zhang, Z. (2018) · 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS) · doi:10.1109/iwqos.2018.8624183 · Cited by 1,400
Super-convergence: very fast training of neural networks using large learning rates
Smith, L. N., & Topin, N. (2019) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2520589 · Cited by 1,335
REBUS and the anarchic brain: Toward a unified model of the brain action of psychedelics
Carhart-Harris, R. L., & Friston, K. J. (2019) · Pharmacological Reviews · doi:10.1124/pr.118.017160 · Cited by 1,180
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113
Interpretable machine learning: Fundamental principles and 10 grand challenges
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022) · Statistics Surveys · doi:10.1214/21-ss133 · Cited by 958
Yaseen, Z. M., Sulaiman, S. O., Deo, R. C., & Chau, K.-W. (2019) · Journal of Hydrology · doi:10.1016/j.jhydrol.2018.11.069 · Cited by 691
Deep learning based tissue analysis predicts outcome in colorectal cancer
Bychkov, D., Linder, N., Turkki, R., Nordling, S., Kovanen, P. E., Verrill, C., Walliander, M., Lundin, M., Haglund, C., & Lundin, J. (2018) · Scientific Reports · doi:10.1038/s41598-018-21758-3 · Cited by 644
Learning to Learn Using Gradient Descent
Hochreiter, S., Younger, A. S., & Conwell, P. R. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-44668-0_13 · Cited by 553
Self-citationThe Marginal Value of Adaptive Gradient Methods in Machine Learning
Wilson, A., Roelofs, R., Stern, M., Srebro, N., & Recht, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.08292 · Cited by 522
Sharpness-Aware Minimization for Efficiently Improving Generalization
Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020) · arXiv · doi:10.48550/arxiv.2010.01412 · Cited by 521
Toward a method of selecting among computational models of cognition.
Pitt, M. A., Myung, I. J., & Zhang, S. (2002) · Psychological Review · doi:10.1037//0033-295x.109.3.472 · Cited by 506
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
Gardner, J. R., Pleiss, G., Bindel, D., Weinberger, K. Q., & Wilson, A. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.11165 · Cited by 496
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
Dong, Z., Yao, Z., Gholami, A., Mahoney, M., & Keutzer, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00038 · Cited by 492
“ll known, based on the theory of Minimum Description Length (MDL), that fewer bits are required to specify a flat region up to a given threshold, and vice versa for a region with sharp curvature [29], [12]. The intuition for this is that the noise created by imprecise location of a flat region is not magnified for a flat…”
BackgroundReimers, N., & Gurevych, I. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1035 · Cited by 463
“As (informally) defined by Hochreiter and Schmidhuber (1997a), a minimum can be flat, where the error function remains approximately constant for a large connected region in weight-space, or it can be sharp, where the error function increases rapidly in”
BackgroundLong short-term memory for machine remaining life prediction
Zhang, J., Wang, P., Yan, R., & Gao, R. X. (2018) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2018.05.011 · Cited by 463
Chen, J., Zeng, G.-Q., Zhou, W., Du, W., & Lu, K.-D. (2018) · Energy Conversion and Management · doi:10.1016/j.enconman.2018.03.098 · Cited by 419
Li, J., Chen, J., Tang, Y., Wang, C., Landman, B. A., & Zhou, S. K. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102762 · Cited by 389
A dual-LSTM framework combining change point detection and remaining useful life prediction
Shi, Z., & Chehade, A. (2021) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2020.107257 · Cited by 351
Hu, Y.-L., & Chen, L. (2018) · Energy Conversion and Management · doi:10.1016/j.enconman.2018.07.070 · Cited by 330
Cust, E. E., Sweeting, A. J., Ball, K., & Robertson, S. (2019) · Journal of Sports Sciences · doi:10.1080/02640414.2018.1521769 · Cited by 324
Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network
Raghunath, S., Ulloa Cerna, A. E., Jing, L., vanMaanen, D. P., Stough, J., Hartzel, D. N., Leader, J. B., Kirchner, H. L., Stumpe, M. C., Hafez, A., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0870-z · Cited by 314
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Bhatt, U., Antorán, J., Zhang, Y., Liao, Q. V., Sattigeri, P., Fogliato, R., Melançon, G., Krishnan, R., Stanley, J., Tickoo, O., et al. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462571 · Cited by 300
Entropy-SGD: biasing gradient descent into wide valleys*
Chaudhari, P., Choromanska, A., Soatto, S., LeCun, Y., Baldassi, C., Borgs, C., Chayes, J., Sagun, L., & Zecchina, R. (2019) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/ab39d9 · Cited by 291
Online Incremental Machine Learning Platform for Big Data-Driven Smart Traffic Management
Nallaperuma, D., Nawaratne, R., Bandaragoda, T., Adikari, A., Nguyen, S., Kempitiya, T., De Silva, D., Alahakoon, D., & Pothuhera, D. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2924883 · Cited by 290
Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals
Ay, B., Yildirim, O., Talo, M., Baloglu, U. B., Aydin, G., Puthankattil, S. D., & Acharya, U. R. (2019) · Journal of Medical Systems · doi:10.1007/s10916-019-1345-y · Cited by 289
Ghimire, S., Yaseen, Z. M., Farooque, A. A., Deo, R. C., Zhang, J., & Tao, X. (2021) · Scientific Reports · doi:10.1038/s41598-021-96751-4 · Cited by 288
Emergence of Invariance and Disentanglement in Deep Representations
Achille, A., & Soatto, S. (2018) · 2018 Information Theory and Applications Workshop (ITA) · doi:10.1109/ita.2018.8503149 · Cited by 267
Tiwary, S., Levy, R., Gutenbrunner, P., Salinas Soto, F., Palaniappan, K. K., Deming, L., Berndl, M., Brant, A., Cimermancic, P., & Cox, J. (2019) · Nature Methods · doi:10.1038/s41592-019-0427-6 · Cited by 256
A survey on few-shot class-incremental learning
Tian, S., Li, L., Li, W., Ran, H., Ning, X., & Tiwari, P. (2024) · Neural Networks · doi:10.1016/j.neunet.2023.10.039 · Cited by 220
Kratzert, F., Klotz, D., Hochreiter, S., & Nearing, G. S. (2021) · Hydrology and Earth System Sciences · doi:10.5194/hess-25-2685-2021 · Cited by 213
Self-citationSentience and the Origins of Consciousness: From Cartesian Duality to Markovian Monism
Friston, K. J., Wiese, W., & Hobson, J. A. (2020) · Entropy · doi:10.3390/e22050516 · Cited by 186
Deep learning generalizes because the parameter-function map is biased towards simple functions
Valle-Pérez, G., Camargo, C. Q., & Louis, A. A. (2018) · arXiv · doi:10.48550/arxiv.1805.08522 · Cited by 105
Wireless Network Intelligence at the Edge
Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2941458 · Cited by 92
On the Existence of Simpler Machine Learning Models
Semenova, L., Rudin, C., & Parr, R. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533232 · Cited by 90
“Based on a minimum-message-length argument (Wallace and Boulton, 1968), several works claim that flat loss functions lead to better generalization due to a robustness to noise around the minimum (Hochreiter and Schmidhuber, 1997; Keskar et al., 2016; Chaudhari et al., 2019).”
BackgroundMethodGrokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Power, A., Burda, Y., Edwards, H., Babuschkin, I., & Misra, V. (2022) · arXiv · doi:10.48550/arxiv.2201.02177 · Cited by 83
On Warm-Starting Neural Network Training
Ash, J. T., & Adams, R. P. (2019) · arXiv · doi:10.48550/arxiv.1910.08475 · Cited by 77
Schmidhuber, J. (2003) · Natural Computing Series · doi:10.1007/978-3-642-18965-4_23 · Cited by 65
Self-citationDegeneracy and Redundancy in Active Inference
Sajid, N., Parr, T., Hope, T. M., Price, C. J., & Friston, K. J. (2020) · Cerebral Cortex · doi:10.1093/cercor/bhaa148 · Cited by 49
Reimers, N., & Gurevych, I. (2018) · arXiv · doi:10.48550/arxiv.1803.09578 · Cited by 30
Deep Learning Is Singular, and That’s Good
Wei, S., Murfet, D., Gong, M., Li, H., Gell-Redman, J., & Quella, T. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3167409 · Cited by 26
Mathematical Models of Overparameterized Neural Networks
Fang, C., Dong, H., & Zhang, T. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3048020 · Cited by 26
“For example, several researchers observed that NN’s generalization ability is related to the sharpness/flatness of the local minimal solution resulted from training and discussed different methods to characterize flatness [91]–[93].”
BackgroundData Augmented Flatness-aware Gradient Projection for Continual Learning
Yang, E., Shen, L., Wang, Z., Liu, S., Guo, G., & Wang, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00518 · Cited by 18
AAontology: An Ontology of Amino Acid Scales for Interpretable Machine Learning
Breimann, S., Kamp, F., Steiner, H., & Frishman, D. (2024) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168717 · Cited by 15
Haghighatlari, M., Marze, N., Seward, R., Ciarla, A., Hindin, R., Calderini, J., Keenan, B., Dhule, S., Hall-Swan, S., Hickling, T. P., et al. (2025) · Communications Biology · doi:10.1038/s42003-025-08500-2 · Cited by 7
Revisiting Flatness-Aware Optimization in Continual Learning With Orthogonal Gradient Projection
Yang, E., Shen, L., Wang, Z., Liu, S., Guo, G., Wang, X., & Tao, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3539019 · Cited by 5
A study on the plasticity of neural networks
Berariu, T., Czarnecki, W., De, S., Bornschein, J., Smith, S., Pascanu, R., & Clopath, C. (2021) · arXiv · doi:10.48550/arxiv.2106.00042 · Cited by 3
“One plausible hypothesis for the occurrence of the generalisation gap stems from the flat versus sharp minima view on generalisation (Hochreiter & Schmidhuber, 1997).”
Background
Metadata
- Authors
- Hochreiter, S., & Schmidhuber, J.
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 1997-01-01
- Volume
- 9
- Issue
- 1
- Pages
- 1-42
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2912811302
- Cited by
- 676
- References
- 42
- FWCI
- 11.41
- 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.