The paper explores the limits of deep neural networks in approximating various function classes.
problem Characterizing the limits of deep neural networks in function approximation.
method Develops a theory relating function complexity and network complexity, using Kolmogorov complexity.
result Deep networks are optimal approximants for various function classes and provide exponential approximation accuracy.
Improved neural network approximates analytic and L^p functions efficiently.
problem Efficiently approximating analytic and L^p functions using neural networks.
method Three-dimensional ReLU network architecture for sawtooth functions, improving approximation rates.
result Substantially improved exponential approximation rates for analytic functions and general L^p functions.
Optimal function approximation with Relu neural networks achieves minimal error.
problem Finding the minimal error in approximating convex functions with Relu networks.
method Established necessary and sufficient conditions for optimal approximations, presented neural network architectures, and proposed an algorithm for convergence.
result Proved the convergence of the proposed algorithm and validated it with experimental results.
Gradient descent trains shallow neural networks to approximate functions in 1D.
problem Approximating functions in 1D with shallow neural networks trained by gradient descent.
method Gradient descent optimization of non-convex weight space for finite width networks in 1D.
result Gradient descent can approximate functions in 1D with a minimal number of weights, balancing practical performance and theoretical capabilities.
AXNet combines two neural networks into one for efficient approximate computing.
problem Efficient approximate computing for error-resilient applications.
method End-to-end trainable AXNet architecture that fuses approximator and predictor.
result Significant improvement in invocation rate and reduction in training time.
Neural networks can approximate functions uniformly across various measures.
problem Universal approximation of functions across different probability measures.
method Proving neural networks are dense in Orlicz spaces, extending classical theorems.
result Neural networks uniformly approximate functions for weakly compact families of measures.
Dense neural networks can't approximate all functions.
problem Approximation capabilities of dense neural networks.
method Model compression approach combining weak regularity lemma and graph neural networks.
result Existence of Lipschitz continuous functions not approximable by dense neural networks.
Dropout neural networks can approximate any function with high probability.
problem Approximating functions with dropout neural networks.
method Two universal approximation theorems for dropout neural networks in random and deterministic modes.
result Dropout neural networks can approximate any function in probability and in Lq. New bounds on ReLU networks for low-regular functions.
problem Bounding approximation error for ReLU networks on low-regular functions.
method Complexity analysis of Fourier features residual networks to ReLU networks.
result Approximation error bound proportional to target function norm and inversely proportional to network width and depth.
Deep neural networks can approximate functions with varying complexity.
problem Understanding the expressivity of deep neural networks in terms of function approximation.
method Using approximation theory, the study measures complexity by connections or neurons, and defines approximation spaces.
result Deep neural networks can approximate functions with low Besov smoothness if sufficiently deep, even with ReLU activation.
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.
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). Study shows limits on deep and shallow neural networks for approximating compact sets.
problem Understanding the limitations of deep and shallow neural networks in approximating compact sets.
method Proved Carl's type inequalities for approximation error, using Lipschitz widths.
result Lower bounds on approximation error for neural network outputs.
This paper quantifies how well random neural networks can approximate continuous functions.
problem Approximating continuous functions with random neural networks.
method Investigates three types of random neural networks: infinite width, subsampled, and corrected. Analyzes approximation rates and provides bounds.
result A function can be approximated with complexity proportional to δ and d. Deep networks can learn functions approximated by shallow networks, but not all functions.
problem The learnability of functions by deep neural networks and the approximation capacity of simpler classes.
method Study the connection between learnability and approximation capacity of functions by deep neural networks and simpler classes.
result A necessary condition for a function to be learnable by deep neural networks is to be approximable by shallow networks.
Investigates neural network approximation power with bounds.
problem Understanding neural network capacity for approximation.
method Established lower and upper bounds on network size and difference.
result Improved bounds for certain function classes.
New RBF networks can approximate any continuous function.
problem Approximating any continuous function on a compact subset.
method Replacing smoothing factors with shifts in RBF networks and proving approximation under certain conditions.
result RBF networks can approximate any continuous function on any compact subset.
Deep neural networks approximate functions in shift-invariant spaces with controlled error.
problem Approximating functions in shift-invariant spaces with neural networks.
method Using deep ReLU neural networks, estimating approximation error bounds based on network width and depth.
result Deep neural networks achieve optimal approximation rates for Sobolev spaces up to a logarithmic factor.
The paper bounds neural networks' approximation error and applies it to regression and GANs.
problem Bounding the approximation error of norm-constrained neural networks.
method Proved upper and lower bounds on approximation error using Rademacher complexity.
result Obtained convergence rates for over-parameterized neural networks and optimal GAN learning rates.
Paper shows deep neural networks can approximate Korobov functions nearly optimally.
problem Approximating Korobov functions with deep neural networks.
method Used deep neural networks and measured approximation rates with Lp and H1 norms. result Achieved a super-convergence rate, outperforming traditional methods.
Deep neural networks with piecewise-polynomial activations can approximate smooth functions and their derivatives.
problem Approximating smooth functions and their derivatives with neural networks.
method Derives the depth, width, and sparsity required for approximation in Hölder norms.
result Deep neural networks with bounded weights can approximate Hölder smooth functions and their derivatives.
Complex-valued neural networks can approximate any continuous function.
problem Generalizing the universal approximation theorem to complex-valued networks.
method Characterizing activation functions for complex networks to approximate any continuous function.
result Different activation functions are required for deep vs shallow complex networks to achieve universal approximation.
A new Kolmogorov-Arnold network improves function approximation and optimization.
problem Approximating potentially irregular functions in high dimensions.
method Proposes a new Kolmogorov-Arnold network (KAN) and provides error bounds and universal approximation theorems.
result Outperforms multilayer perceptrons in accuracy and convergence speed for irregular functions.
Deep networks with path norm regularization can approximate analytic functions.
problem Approximating analytic functions with neural networks.
method Path norm regularized deep networks with activation function.
result Deep networks can approximate analytic functions with logarithmic dependence on approximation error.
Minimum width for ReLU networks to approximate L^p functions is max(d_x+1, d_y).
problem Characterizing the minimum width for ReLU networks to approximate L^p functions.
method Analyzing networks with ReLU activation functions and proving the minimum width required.
result The minimum width required for the universal approximation of L^p functions is exactly max(d_x+1, d_y).
Paper proves neural networks can be approximated using interval bounds.
problem Verifying safety and robustness of neural networks.
method Introduces interval universal approximation (IUA) theorem for neural networks.
result Neural networks can be approximated using interval bounds for any continuous function and squashable activation functions.
Novel method uses MCMC to improve approximation networks.
problem Approximating complex, intractable distributions.
method Amortized MCMC with iterative refinement of approximation network.
result Improved quality of deep generative model training.
Analytic networks with bounded coefficients can't outperform polynomial approximations.
problem Approximation limits of neural networks with analytic activation functions under coefficient constraints.
method Deterministic analysis using comparison argument and Bernstein-type estimates.
result Networks with analytic activation functions and controlled coefficients cannot outperform classical polynomial approximation rates on non-analytic targets.
This paper proves neural networks can approximate any infinite-dimensional map with uniform guarantees.
problem Universal approximation of infinite-dimensional maps by neural networks with uniform guarantees.
method Analysis of various infinite analogues of neural networks and their approximation capabilities.
result Any continuous map can be approximated arbitrarily closely by some infinite neural networks with mild topological conditions.
Deep learning networks are approximated using dynamical systems theory.
problem Understanding the approximation capabilities of deep learning networks.
method Modeling deep residual networks as continuous-time dynamical systems and using approximation theories in Lp. result Established general sufficient conditions for universal approximation of deep residual networks.
Deep neural networks can approximate rough functions with high accuracy.
problem Approximating rough functions with neural networks.
method Proved that ENO interpolation can be cast as a deep ReLU neural network, transferring ENO's high-order accuracy.
result Deep neural networks can achieve high-order accuracy in approximating Lipschitz functions.
TVS-FNNs can approximate any continuous function on expanded input spaces.
problem Processing a broader range of inputs like sequences and matrices.
method Proving a universal approximation theorem for TVS-FNNs.
result TVS-FNNs can approximate any continuous function on expanded input spaces.
Efficiently approximates neural network function space distance.
problem Estimating the average discrepancy between neural network outputs.
method Linearized Activation Function TRick (LAFTR) for ReLU networks.
result Parametric approximation outperforms nonparametric methods in memory and accuracy.
Survey examines deep neural networks' ability to approximate functions.
problem Approximation of target functions by deep neural networks.
method Examination of feed-forward and residual architectures, focusing on optimization problems in regression and classification.
result Deep neural networks can approximate functions effectively, especially with ReLU activation functions.
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.
Review of neural network expressivity and architectures.
problem Understanding neural network expressivity across different architectures.
method Comprehensive overview of approximation results for various neural network types.
result Deep neural networks offer advantages over shallow ones for specific function classes.
The paper proves deep neural networks with analytic activation can approximate any function.
problem Approximating functions with neural networks using analytic activation functions.
method Elementary proofs for real and complex networks, Stone-Weierstrass theorem, Mergelyan's theorem.
result Closure of neural network classes equals space of polynomials for analytic activation.
Study shows how to approximate functions using neural networks.
problem Approximating measurable functions on hypercube.
method Using affine neural networks to approximate measurable functions.
result Any measurable function can be approximated by a bounded number of neurons.
We developed safe and ranged approximations for ReLU, tanh, and sigmoid functions to reduce neural network training time.
problem Expensive computation of hyperbolic tangent and sigmoid functions in neural networks.
method Function approximation techniques to create safe and ranged approximations.
result 10% to 37% improvement in training times on CPU and 20% to 53% improvement in ranged cases.
Paper connects neural network score approximation to reverse diffusion model distribution approximation.
problem Quantifying the relationship between neural network score approximation and the distribution generated by reverse diffusion models.
method Combines Hornik's universal approximation theorem, Girsanov's theorem, and data processing inequality.
result Neural network score approximation guarantees distribution approximation in reverse diffusion models.
Deep neural networks with various activation functions can approximate Hölder smooth functions.
problem Expressivity of deep neural networks with general activation functions.
method Investigates approximation ability of deep neural networks with a broad class of activation functions, including Hölder smooth functions.
result Derives the required depth, width, and sparsity of deep neural networks to approximate Hölder smooth functions.
Neural networks can approximate any L^p functions on R^n.
problem Approximating functions on unbounded domains with neural networks.
method Monotone sigmoid, ReLU, ELU, Softplus, LeakyReLU activation functions.
result Shallow neural networks can arbitrarily well approximate L^p functions on R^n.
Deep Neural Network approximates Bayesian Network posterior probabilities efficiently.
problem Approximating Bayesian Network posterior probabilities efficiently.
method Using Deep Neural Network to learn joint probability distribution from few observation and posterior probability pairs.
result Deep Neural Network achieves high accuracy in approximating Bayesian Network posterior probabilities, faster and more accurate than traditional methods.
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.
Formula found for neural network error with fixed weights.
problem Understanding error in neural networks with fixed weights.
method Provided an explicit formula for approximation error.
result Explicit formula for neural network error with fixed weights.
New network approximates functions with error decreasing with network width and depth.
problem Approximating functions with high-dimensional data.
method Floor-ReLU networks with specific width and depth.
result Approximation error decreases as network width and depth increase.
The paper shows neural networks can approximate functions over non-compact domains with non-polynomial activation.
problem Approximating functions over non-compact domains using neural networks.
method Using single-hidden-layer feedforward neural networks with non-polynomial activation functions over non-compact subsets of Euclidean spaces.
result Neural networks can approximate functions in weighted Ck-spaces and weighted Sobolev spaces over unbounded domains. The paper shows how neural networks can approximate PDEs with polynomial scaling in dimension.
problem Understanding the complexity of approximating PDE solutions with neural networks.
method Developed a proof technique to simulate gradient descent using neural networks.
result Neural network parameters scale polynomially with input dimension for approximating PDE solutions.