Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations

The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined deep learning, revolutionized the area...

cs.LG math.NA stat.ML Mathematics Computer Science

Source

Paper

References (90)

01How degenerate is the parametrization of neural networks with the ReLU activation function?Julius Berner, Dennis Elbrächter, P. Grohs2019 · Neural Information Processing Systems · 31 citations In Library

02Decay in the one dimensional generalized Improved Boussinesq equationC. Maulén, Claudio Muñoz2019 · SN Partial Differential Equations and Applications · 14 citations

03A Theoretical Analysis of Deep Neural Networks and Parametric PDEsGitta Kutyniok, P. Petersen, Mones Raslan et al.2019 · Constructive approximation · 226 citations In Library

04Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systemsChristoph Reisinger, Yufei Zhang2019 · Analysis and Applications · 73 citations In Library

05A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equationsMartin Hutzenthaler, Arnulf Jentzen, T. Kruse et al.2019 · SN Partial Differential Equations and Applications · 172 citations In Library

06Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQC. Schwab, J. Zech2018 · Analysis and Applications · 191 citations

07Gradient Descent Finds Global Minima of Deep Neural NetworksS. Du, J. Lee, Haochuan Li et al.2018 · International Conference on Machine Learning · 1.3k citations In Library

08Dynamic ProgrammingR. Oka, Aizu Wakamatsu2018 · Wiley Encyclopedia of Computer Science and Engineering · 3.6k citations

09DNN Expression Rate Analysis of High-Dimensional PDEs: Application to Option PricingDennis Elbrächter, P. Grohs, Arnulf Jentzen et al.2018 · Constructive approximation · 118 citations

10A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficientsArnulf Jentzen, Diyora Salimova, Timo Welti2018 · Communications in Mathematical Sciences · 123 citations In Library

11A Convergence Theory for Deep Learning via Over-ParameterizationZeyuan Allen-Zhu, Yuanzhi Li, Zhao Song2018 · International Conference on Machine Learning · 1.7k citations In Library

12Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured DataYuanzhi Li, Yingyu Liang2018 · Neural Information Processing Systems · 686 citations In Library

Scroll for more · 38 remaining

Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU NetsShao-Bo Lin, Yao Wang, Ding‐Xuan Zhou2021 · arXiv (Cornell University) In Library

Generalization Performance of Empirical Risk Minimization on Over-Parameterized Deep ReLU NetsShao-Bo Lin, Yao Wang, Ding‐Xuan Zhou2025 · IEEE Transactions on Information Theory In Library

Empirical risk minimization in the interpolating regime with application to neural network learningNicole Mücke, Ingo Steinwart2025 · Machine Learning In Library

Deep Empirical Risk Minimization in finance: looking into the futureA. Max Reppen, H. Meté Soner2020 · arXiv (Cornell University) In Library

A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equationsP. Grohs, F. Hornung, Arnulf Jentzen et al.2018 · Memoirs of the American Mathematical Society · 189 citations In Library

Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimesJulius Martinetz, Christoph Linse, Thomas Martinetz2024 In Library

An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers.Ramakrishna Vedantam, David López-Paz, David J. Schwab2021 · PubMed In Library

On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural NetworksA. Backurs, P. Indyk, Ludwig Schmidt2017 · Neural Information Processing Systems · 45 citations In Library

An Empirical Investigation of Domain Generalization with Empirical Risk MinimizersRamakrishna Vedantam2021 · Neural Information Processing Systems · 47 citations In Library

Patents near this paper

MINIMIZING GLOBAL ERROR IN AN ARTIFICIAL NEURAL NETWORKUS 10,068,170 · ORACLE INTERNATIONAL CORPORATION · 2018 DISPARITY MITIGATION IN MACHINE LEARNING-BASED PREDICTIONS FOR DISTINCT CLASSES OF DATA USING DERIVED INDISCERNIBILITY CONSTRAINTS DURING NEURAL NETWORK TRAININGUS 11,676,037 · FAIRNESS-AS-A-SERVICE, INC · 2023 Neural Network ClassifierUS 11,049,011 · INDIAN INSTITUTE OF TECHNOLOGY DELHI · 2021 Analytic And Empirical Correction Of Biased Error Introduced By Approximation MethodsUS 11,604,987 · QUALCOMM INCORPORATED · 2023 OPTIMIZATION OF MODEL GENERATION IN DEEP LEARNING NEURAL NETWORKS USING SMARTER GRADIENT DESCENT CALIBRATIONUS 11,120,333 · INTERNATIONAL BUSINESS MACHINES CORPORATION · 2021

Source of record

arXiv

Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations

Paper

References (90)

Similar papers

Patents near this paper

Welcome.

Patents near this paper