A selective overview of deep learning
From MaRDI portal
Publication:2038303
DOI10.1214/20-STS783WikidataQ112690530 ScholiaQ112690530MaRDI QIDQ2038303
Cong Ma, Yiqiao Zhong, Jianqing Fan
Publication date: 6 July 2021
Published in: Statistical Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1904.05526
neural networksoverparametrizationapproximation theorystochastic gradient descentgeneralization error
Related Items
Discussion to: \textit{Bayesian graphical models for modern biological applications} by Y. Ni, V. Baladandayuthapani, M. Vannucci and F.C. Stingo, Marginally Calibrated Deep Distributional Regression, Adversarial Machine Learning: Bayesian Perspectives, Data augmentation for Bayesian deep learning, Recent advances in reinforcement learning in finance, Individualized risk assessment of preoperative opioid use by interpretable neural network regression, Understanding Implicit Regularization in Over-Parameterized Single Index Model, Can a Machine Correct Option Pricing Models?, Detecting conflicting summary statistics in likelihood-free inference, Special issue on statistical analysis of networks, A review of h-likelihood for survival analysis, Measurement error models: from nonparametric methods to deep neural networks, Provably training overparameterized neural network classifiers with non-convex constraints, Robust deep neural network estimation for multi-dimensional functional data, A new deep neural network algorithm for multiple stopping with applications in options pricing
Uses Software
Cites Work
- Bagging predictors
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Additive regression and other nonparametric models
- A finite sample distribution-free performance bound for local discrimination rules
- The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
- Heuristics of instability and stabilization in model selection
- Why does deep and cheap learning work so well?
- Optimal global rates of convergence for nonparametric regression
- Random approximants and neural networks
- On the near optimality of the stochastic approximation of smooth functions by neural networks
- Analysis of a two-layer neural network via displacement convexity
- Nonparametric regression using deep neural networks with ReLU activation function
- On deep learning as a remedy for the curse of dimensionality in nonparametric regression
- Optimal smoothing in single-index models
- Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
- An Efficient Learning Procedure for Deep Boltzmann Machines
- Distribution-free performance bounds for potential function rules
- Acceleration of Stochastic Approximation by Averaging
- Universal approximation bounds for superpositions of a sigmoidal function
- Ideal spatial adaptation by wavelet shrinkage
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- 10.1162/153244302760200704
- Neural Network Learning
- A mean field view of the landscape of two-layer neural networks
- Size-independent sample complexity of neural networks
- Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
- Deep Knockoffs
- Reconciling modern machine-learning practice and the classical bias–variance trade-off
- Mean Field Analysis of Neural Networks: A Law of Large Numbers
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Understanding Machine Learning
- On the Structure of Continuous Functions of Several Variables
- Some methods of speeding up the convergence of iteration methods
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Stochastic Estimation of the Maximum of a Regression Function
- A Stochastic Approximation Method
- Approximation by superpositions of a sigmoidal function
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
