Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
The paper analyzes deep ReLU CNNs' approximation properties in 2D space.
problem Establishing L2 approximation properties for deep ReLU CNNs. method Analysis based on decomposition theorem for convolutional kernels, properties of ReLU activation, and connections with one-hidden-layer ReLU NNs.
result Universal approximation theorem for deep ReLU CNNs with classic structure.
The paper proves deep ReLU networks avoid spurious local minima in NTK regime.
problem The existence of spurious local minima in deep ReLU neural networks.
method Theoretical proof under Neural Tangent Kernel regime.
result Deep ReLU networks do not lie in spurious local minima in NTK regime.
Deep ReLU networks estimate Hölder functions on low-dimensional manifolds with fast convergence.
problem Estimating Hölder functions on low-dimensional manifolds with noisy data.
method Deep ReLU network architecture designed for nonparametric regression.
result Empirical estimator convergence rate of n−2(s+α)+d2(s+α)log3n. Researchers can reverse-engineer deep ReLU networks from outputs.
problem Recovering a deep ReLU network from its outputs.
method Dissecting region boundaries to identify neuron states and weights.
result Weights and neuron arrangement of a deep ReLU network can be recovered.
This paper examines how noise affects deep neural networks and improves their performance.
problem The impact of noise on the stability of deep ReLU neural networks for nonparametric regression.
method Investigates the optimal rate of convergence for deep ReLU neural networks under Huber loss, considering the p-th moment of noise and the smoothness of the function.
result The optimal rate of convergence cannot be achieved by ordinary least squares but can be by Huber loss with a properly chosen parameter.
Deep ReLU networks need Ω(N) parameters to interpolate at irregularly spaced points.
problem Interpolating at irregularly spaced data points with deep ReLU networks.
method Analyzing the number of parameters required for interpolation.
result Ω(N) parameters are necessary for interpolation when δ is exponentially small in N.
Study approximates nonlinear functionals using deep ReLU networks.
problem Approximating nonlinear continuous functionals with neural networks.
method Constructs continuous piecewise linear interpolation under simple triangulation, analyzes rates of approximation.
result Established rates of approximation for functional deep ReLU networks.
Gradient descent optimizes deep ReLU networks with proper initialization.
problem Training deep neural networks with ReLU activation.
method Gradient descent and stochastic gradient descent with proper random weight initialization.
result Gradient descent finds global minima for over-parameterized deep ReLU networks.
Gradient descent methods for deep ReLU networks achieve optimal generalization rates.
problem Generalization of gradient descent methods for deep neural networks
method Establishing minimax-optimal rates for GD and SGD with deep ReLU networks
result Gradient descent methods for deep ReLU networks achieve optimal generalization rates
Gradient descent with logistic loss can interpolate deep networks with smoothed ReLU activations under certain conditions.
problem Conditions for gradient descent to drive logistic loss to zero in deep networks with smoothed ReLU activations.
method Gradient descent applied to fixed-width deep networks with smoothed ReLU approximations (e.g., Swish, Huberized ReLU).
result Gradient descent can drive logistic loss to zero under specific conditions, providing bounds on convergence rate.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
Deep ReLU networks have surprisingly few activation patterns at initialization.
problem Limited expressivity of deep ReLU networks despite theoretical potential.
method Analyzed the number of activation patterns in ReLU networks at initialization and during training.
result The average number of activation patterns is bounded by the total number of neurons raised to the input dimension.
Bayesian free energy remains bounded for deep ReLU networks in overparametrized cases.
problem Understanding the generalization performance of deep ReLU neural networks.
method Analyzes Bayesian free energy in overparametrized deep ReLU neural networks.
result Bayesian free energy is bounded even in overparametrized deep ReLU networks.
Deep ReLU networks can approximate smooth functions nearly optimally.
problem Approximating smooth functions with deep neural networks.
method Using Taylor expansions and deep ReLU network approximations, the paper establishes optimal approximation error bounds.
result Deep ReLU networks of width and depth O(NlnN) and O(LlnL) can approximate f∈Cs([0,1]d) with an error O(∥f∥Cs([0,1]d)N−2s/dL−2s/d). Deep ReLU networks can approximate matrix-vector products with error bounds.
problem Can deep ReLU networks accurately approximate matrix-vector products?
method Derived error bounds in Lebesgue and Sobolev norms for deep ReLU FNNs.
result Developed deep approximation theory with successful applications.
Adam achieves optimal convergence in deep ReLU networks via novel Kakeya bounds.
problem Training deep ReLU networks using Adam in non-smooth settings.
method Stratified Morse theory and Kakeya bounds to analyze region crossings and convergence.
result First global-optimal convergence for Adam in non-smooth, non-convex ReLU landscapes.
New research shows deep ReLU networks can be learned with polylogarithmic width.
problem Learning deep ReLU networks with limited over-parameterization.
method Using gradient descent, the study establishes learning guarantees for networks with polylogarithmic width.
result Deep ReLU networks can be learned with a polylogarithmic width condition, not just a high degree polynomial.
Proposes a new theoretical framework for deep locally connected ReLU networks.
problem Understanding theoretical properties of deep locally connected networks.
method Teacher-student setting, explicit formulation of data distribution, disentangled representations, compatibility with regularization techniques.
result Theoretical framework facilitates analysis of practical issues like overfitting and generalization.
Improved bounds on neural network expressivity.
problem Understanding neural network expressivity and approximation capabilities.
method Improved bounds on the maximal number of linear regions of ReLU-networks.
result New insights into the expressivity of neural networks.
Deep ReLU networks can approximate various signal types with exponential error decay.
problem Approximating different signal structures with deep neural networks.
method Demonstrated approximation of polynomials, sinusoidal functions, oscillatory textures, and fractals.
result Finite-width deep ReLU networks require fewer connections than wide finite-depth networks for smooth function approximation.
New theory for local parameterization of deep ReLU networks.
problem Determining local parameters of deep ReLU neural networks.
method Introducing local lifting operators and charts of a manifold, deriving necessary and sufficient conditions for local identifiability.
result Sharp and testable conditions for local identifiability of deep ReLU networks.
The paper proves deep ReLU networks can die and proposes a new initialization method to prevent it.
problem Dying ReLU neurons in deep neural networks.
method The paper rigorously proves the dying ReLU problem and proposes a new randomized asymmetric initialization method.
result The new initialization method effectively prevents the dying ReLU problem.
The paper reveals how clustering in ReLU networks enhances interpretability.
problem Improving interpretability of deep learning models.
method Clustering of ReLU neuron patterns to reveal underlying affine maps.
result The network's predictions can be explained by feature importance within clusters.
This paper simplifies deep ReLU networks into local linear models for better interpretability.
problem Limited transparency and interpretability of deep neural networks, especially ReLU networks.
method Local linear representation and equivalent set of local linear models (LLMs).
result Simplified deep ReLU networks for better interpretability and diagnostics.
This study examines how reward scaling impacts non-saturating ReLU networks in reinforcement learning.
problem The impact of reward scaling on non-saturating ReLU networks in reinforcement learning.
method Proposes an Adaptive Network Scaling framework to find a suitable reward scale during learning.
result Empirical studies justify the effectiveness of the Adaptive Network Scaling framework.
Path regularization reveals convex optimization in deep ReLU networks.
problem Understanding the optimization landscape of deep neural networks.
method Introducing path regularization to make the training problem convex and sparsity-inducing.
result Path regularized parallel ReLU networks are a parsimonious convex model in high dimensions.
New properties of deep ReLU networks at initialization improve performance.
problem Improving performance of deep ReLU networks.
method PAC analysis framework to prove novel properties of He initialization.
result Hidden activation norms and weight gradient norms are preserved under He initialization.
New method reveals properties of ReLU-networks via invertibility.
problem Understanding the behavior of deep neural networks.
method Deriving a theory on invertibility of ReLU-layers and exploring mechanisms affecting stability.
result Numerical results show characteristic properties of ReLU-networks.
New activations improve deep network reproducibility without sacrificing accuracy.
problem Deep networks' reproducibility issues, especially on distributed systems.
method Developed SmeLU activations, smoother than ReLU, to enhance reproducibility.
result SmeLU activations provide better accuracy-reproducibility tradeoffs.
Deep ReLU networks escape from the origin via saddle points with a low-rank bias.
problem Understanding the dynamics of gradient descent in deep ReLU networks.
method Analysis of escape directions and singular values of weight matrices.
result The first singular value of the ℓ-th layer weight matrix is at least ℓ41 larger than any other singular value. Deep ReLU networks can approximate functions on manifolds with high accuracy.
problem Approximating functions defined on manifolds with high accuracy.
method Sparsely connected deep ReLU networks for approximation.
result Deep ReLU networks can approximate Hölder functions on manifolds with error ε using a number of parameters proportional to ε−d∗/βlog(1/ε). Study reveals how initial weights influence convergence in deep ReLU networks.
problem Understanding the dynamics and generalization of deep ReLU networks.
method Teacher-student setting, gradient analysis, and activation assumptions.
result Initial weights close to teacher nodes lead to faster convergence, and fan-out weights of other nodes converge to zero in over-parameterized cases.
Deep neural networks with ReLU activation achieve optimal nonparametric regression rates.
problem Nonparametric regression with general composition assumptions.
method Sparsely connected deep neural networks with ReLU activation function.
result Achieve minimax rates of convergence under general composition assumption.
Optimal rates for shallow ReLU networks in nonparametric regression.
problem Approximating smooth and non-smooth functions with shallow ReLU networks.
method Analysis of shallow ReLUk neural networks, using variation norms and deep learning theory. result Optimal approximation rates for shallow ReLU networks in nonparametric regression.
Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.
problem Binary classification of unbounded Gaussian mixture data.
method Deep ReLU neural networks with non-asymptotic upper bounds and convergence rates.
result Deep ReLU networks can classify unbounded Gaussian mixture data without dimensionality constraints.
Paper improves confidence intervals and variance estimation for deep learning models.
problem Improving confidence intervals and variance estimation in deep learning models.
method Residual-based framework for conditional variance estimation; robust bootstrap procedure for confidence intervals.
result First non-asymptotic bounds for variance estimation using ReLU networks.
A new activation function FTS improves deep learning performance.
problem Hindered propagation of negative values in ReLU.
method Proposed Flatten-T Swish (FTS) activation function, evaluated on MNIST dataset.
result FTS with T=-0.20 improves MNIST classification accuracy by 1.15% on 8-layer DFNN.
Deep ReLU networks approximate as well as shallow ones in kernel regimes.
problem Understanding the limitations of kernel methods for deep ReLU networks.
method Characterizing eigenvalue decays of kernels derived from deep ReLU networks.
result Deep ReLU networks and shallow two-layer networks have equivalent approximation properties in kernel regimes.
Deep ReLU networks generalize well with few parameters.
problem Generalization of overparametrized deep neural networks.
method Explicit bounds on test error independent of overparametrization and VC dimension.
result Generalization error is independent of network architecture and overparametrization.
Deep ReLU networks can efficiently approximate Sobolev and Besov functions.
problem Approximating functions in Sobolev and Besov spaces using deep neural networks.
method Used deep ReLU neural networks with varied width and depth to approximate functions in Sobolev and Besov spaces.
result Generalized the approximation rate to hold under the Sobolev embedding condition.
Deep networks can approximate various activation functions with modest adjustments.
problem Expressive power of deep neural networks with diverse activation functions.
method Approximation of any activation function in set A by ReLU networks with specific scaling factors.
result Approximation of any activation function in a specific subset of A by ReLU networks with (1,1) scaling factors.
The paper improves lower bounds on deep neural network trajectories.
problem Understanding the expressivity of deep neural networks.
method Generalized method for lower bounding trajectory growth in random sparse deep ReLU networks.
result Trajectory growth can remain exponential in depth with sparse variants of random nets.
Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.
problem Understanding the expressive power of deep neural networks through function compositions.
method Demonstrated the surprising expressive power of repeated compositions of a single fixed-size ReLU network.
result Repeated compositions of a single fixed-size ReLU network can approximate 1-Lipschitz continuous functions on [0,1]d with an error O(r−1/d). Deep ReLU networks show that 4 layers suffice for unique input recovery.
problem Injectivity capacity of deep ReLU networks.
method Developed a program connecting deep ReLU injectivity to an l-extension of the ℓ0 spherical perceptrons, using random duality theory. result Only 4 layers are needed for unique input recovery, showing expansion saturation effect.
Develops ADMM for deep neural networks with sigmoid activations to avoid saturation and improve approximation.
problem Gradient saturation in deep neural networks with sigmoid activations.
method Introduces sigmoid-ADMM pair for training deep sigmoid nets and proves its convergence.
result ADMM avoids saturation and improves approximation of deep sigmoid nets compared to ReLU nets.
Unified framework reveals regularization mechanism in deep ReLU networks via convex optimization.
problem Understanding the success of deep neural networks.
method Developed a unified framework using convex optimization to reveal regularization mechanisms.
result ReLU networks can be globally optimized via convex programs, enforcing sparsity.
New maximum score estimators using ReLU functions and deep neural networks.
problem Estimating parameters in models with sign restrictions.
method ReLU-based maximum score criterion and DNN architecture.
result RMS estimator achieves n−s/(2s+1) convergence rate and asymptotic normality.