New geometric proof of convex function differentiability and approximation.
problem Second-order differentiability of convex functions and their approximations.
method Elementary geometric approach to prove classical and recent results.
result New proofs of Lusin approximation of convex functions and bodies by C1,1 functions. Universal approximation theorem for differentiable maps on infinite-dimensional manifolds
problem Approximation of differentiable maps on infinite-dimensional manifolds
method Weighted universal approximation theorem
result Universal approximation theorem for differentiable maps
Efficient offline reinforcement learning with neural networks using differentiable function approximation.
problem Statistical efficiency of offline reinforcement learning with function approximators.
method Pessimistic fitted Q-learning (PFQL) and differentiable function approximation.
result Provably efficient offline reinforcement learning with differentiable function approximation.
Generalizes neural network approximation to infinite-dimensional manifolds and derivatives.
problem Approximating differentiable maps on infinite-dimensional manifolds.
method Proves a weighted Nachbin theorem to establish universal approximation for differentiable maps, including derivatives.
result Linear functions of the signature can approximate path space functionals including their derivatives.
Neural networks can approximate complex stochastic equations well.
problem Approximating general stochastic differential equations.
method Identified neural network classes approximating continuous functions.
result Neural stochastic differential equations can approximate general stochastic differential equations arbitrarily well.
Global approximation for piecewise linear paths via signatures.
problem Global approximation theorems for piecewise linear paths.
method Using signatures of piecewise linear paths and their density in Lp-norms. result Linear functionals of signatures are dense in Lp-norms under an integrability condition. In this paper, we present a method for the accurate estimation of the derivative (aka.~sensitivity) of expectations of functions involving an indicator function by combining a stochastic algorithmic differentiation and a regression. The method is an improvement of the approach presented in [Risk Magazine April 2018]. T…
Stochastic differential equation approximation for linear TD(0) under Markovian noise
problem Temporal-difference learning with linear function approximation
method Stochastic differential equation approximation
result Explains the constant-stepsize error floor
Develops a mathematical model for automatic differentiation in machine learning.
problem Current automatic differentiation lacks a simple mathematical model for machine learning.
method Articulates relationships between program differentiation and nonsmooth functions, provides a class of functions and nonsmooth calculus.
result Shows how nonsmooth calculus applies to stochastic approximation methods and evidence of artificial critical points.
Universal approximation for stochastic processes using Brownian motion.
problem Approximating stochastic processes with linear functionals.
method Establishing Lp-type universal approximation theorems for rough path spaces. result Linear functionals on the signature of time-extended Brownian motion can approximate any p-integrable stochastic process. Bayesian approach approximates probability functions of Gaussian mixtures.
problem Approximating probability functions of non-spherical Gaussian mixtures.
method Bayesian decomposition, spherical radial decomposition, random sampling.
result Established differentiability and integral representation of gradient for probability functions.
FNN approximates functions and solves PDEs with periodic BCs.
problem Approximating and solving periodic functions and PDEs.
method Fourier neural network architecture with activation and loss functions.
result FNN can solve PDEs with periodic BCs and is interpretable.
Modern neural network training relies on piece-wise (sub-)differentiable functions in order to use backpropagation to update model parameters. In this work, we introduce a novel method to allow simple non-differentiable functions at intermediary layers of deep neural networks. We do so by training with a differentiable…
We extend neural networks with fractional and mixed activation functions for better function approximation.
problem Limitations in approximating higher-order smooth functions in complex spaces.
method Incorporating fractional exponents in activation functions and defining new density functions.
result Improved accuracy and broader applicability of neural network approximation theory.
FQE with deep neural networks achieves asymptotic normality and finite-sample bounds.
problem Theoretical understanding of FQE with general differentiable function approximators.
method Z-estimation theory applied to FQE with deep neural networks.
result FQE estimation error is asymptotically normal with explicit variance.
Improved set prediction model using multiset-equivariant operations and approximate implicit differentiation.
problem Existing set prediction models struggle with multisets and cannot represent certain functions.
method Introduced multiset-equivariance, improved DSPN with approximate implicit differentiation, and applied to CLEVR object property prediction.
result Significantly improved object property prediction on CLEVR dataset.
We compare the sample complexity of private learning [Kasiviswanathan et al. 2008] and sanitization~[Blum et al. 2008] under pure ε-differential privacy [Dwork et al. TCC 2006] and approximate (ε,δ)-differential privacy [Dwork et al. Eurocrypt 2006]. We show that the sample complexity of these tasks under approxima…
We introduce a nonparametric approach for estimating drift and diffusion functions in systems of stochastic differential equations from observations of the state vector. Gaussian processes are used as flexible models for these functions and estimates are calculated directly from dense data sets using Gaussian process r…
Physics-informed neural networks approximate diffusion process pdfs efficiently.
problem Approximating the probability density function of diffusion processes.
method Physics-informed neural networks solving Fokker-Planck or integro-differential equations.
result Neural network solutions approximate target solutions for various types of differential equations.
We study the finite horizon Merton portfolio optimization problem in a general local-stochastic volatility setting. Using model coefficient expansion techniques, we derive approximations for the both the value function and the optimal investment strategy. We also analyze the `implied Sharpe ratio' and derive a series a…
This paper is concerned with the following Markovian stochastic differential equation of mean-reversion type \[ dR_t= (θ+σα(R_t, t))R_t dt +σR_t dB_t \] with an initial value R0=r0∈R, where θ∈R and σ>0 are constants, and the mean correction function $α:\mathbb{R}\times[0,\infty)\to α(x,t)\…
We develop a new method to solve complex physics equations more accurately and efficiently.
problem Challenges in solving functional differential equations due to high computational costs and inaccurate approximations.
method Combining physics-informed neural networks (PINNs) with cylindrical approximation to handle functional derivatives.
result Our method achieves typical L1 relative error orders of PINNs of ∼10−3 on two FDEs. Paper proves GDL models can approximate any continuous function on non-Euclidean data.
problem Processing non-Euclidean data with universal feedforward models.
method Introduces geometric deep learning framework for differentiable manifold geometries.
result GDL models can uniformly approximate any continuous function on compact sets.
A latent force model is a Gaussian process with a covariance function inspired by a differential operator. Such covariance function is obtained by performing convolution integrals between Green's functions associated to the differential operators, and covariance functions associated to latent functions. In the classica…
INNs can approximate diverse functions despite layer restrictions.
problem Can INNs approximate sufficiently diverse functions?
method Developed a theoretical framework based on differential geometry to simplify the approximation problem of diffeomorphisms.
result INNs have the universal approximation property.
HDNNs can approximate any continuous function, proving their expressivity.
problem Lack of a comprehensive study on the expressivity of HDNNs.
method Discretization of Hamiltonian Neural Ordinary Differential Equations (HNN-ODEs).
result HDNNs can approximate any continuous function over a compact domain.
New method approximates diffusion process posteriors using moment functions.
problem Approximating posteriors of stochastic differential equations.
method Constructs variational process as controlled prior, approximates posterior with moment functions, uses natural gradient descent.
result Richer variational approximations for state-dependent diffusion terms.
The main goal of this paper is to develop a concept of approximate differentiability of higher order for subsets of the Euclidean space that allows to characterize higher order rectifiable sets, extending somehow well known facts for functions. We emphasize that for every subset A of the Euclidean space and for eve…
DQNs can approximate optimal Q-functions with high accuracy on compact sets.
problem Approximating optimal Q-functions in continuous-time Markov Decision Processes.
method Stochastic control, FBSDEs, residual network approximation theorems, large deviation bounds, viscosity solutions.
result DQNs can approximate optimal Q-functions on compact sets with arbitrary accuracy and high probability.
Method uses DNNs to approximate functions with specific asymptotic behavior.
problem Approximating functions with given asymptotic behavior.
method Specifically constructed terms combined with unconstrained DNN.
result Enforcing asymptotic behavior leads to better approximation and faster convergence.
Researchers develop methods to calibrate ABMs using Bayesian techniques.
problem Challenges in calibrating ABMs due to likelihood intractability and non-differentiability.
method Generalised variational inference for differentiable ABMs.
result Accurate Bayesian parameter inferences for differentiable ABMs demonstrated.
We study differential forms and their higher-order generalizations by interpreting them as functions on map spaces. We get a series of approximations of "generalized manifolds" (i.e. of sheaves and stacks) somewhat akin to Taylor series.
Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the discrete view has its intrinsic limitations: there is no characterization of the optim…
Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce privacy by adding random noise to a function computed over the data, and the challenge in designing such algorithms is to control the added…
Paper addresses ERM in LDP, reducing sample complexity for smooth and convex losses.
problem Achieving error α in ERM with non-interactive LDP, especially for high-dimensional data.
method Developed algorithms using Bernstein polynomial and polynomial approximation techniques.
result For smooth and convex losses, sample complexity is linear in dimensionality.
NODEs can approximate a wide range of diffeomorphisms with strong guarantees.
problem The approximation power of NODEs under certain conditions.
method Leveraging a structure theorem of the diffeomorphism group.
result NODEs can approximate a large class of diffeomorphisms with a stronger guarantee.
Proposes a method for approximating transition densities of SDEs driven by gamma processes.
problem Calculating transition densities for SDEs driven by gamma processes.
method Taylor-type approximation and conditional expectation of multiple stochastic integrals.
result Efficiency of the proposed method demonstrated through numerical tests.
We show that finite-width deep ReLU neural networks yield rate-distortion optimal approximation (Bölcskei et al., 2018) of polynomials, windowed sinusoidal functions, one-dimensional oscillatory textures, and the Weierstrass function, a fractal function which is continuous but nowhere differentiable. Together with thei…
Reduces function approximation dimensions from high to low with sparse data.
problem Function approximation from sparse data.
method Nonlinear Level Set Learning (NLL) with geometric information.
result Reduces input dimension to theoretical lower bound with minor accuracy loss.
New method uses PINNs to efficiently compute Gerber-Shiu functions.
problem Calculating the Gerber-Shiu function efficiently.
method Physics-informed neural networks (PINNs) embedded with differential equations.
result Demonstrates good performance in approximating Gerber-Shiu functions.
We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural networks and analyze their approximation capabilities, showing in particular that any Lipschitz-continuous map defined on a hypercube can be unifor…
Deep networks can efficiently approximate functions on curved manifolds.
problem Approximating functions and their derivatives on complex, curved domains.
method Proved constant-depth ReLU networks can approximate functions in Sobolev spaces on manifolds.
result Deep networks with bounded weights can approximate functions in Wpk(Md) to an error of ε using O(ε−d/(k−s)) parameters. New machine learning methods solve complex PDEs with improved accuracy.
problem Solving fully nonlinear PDEs with convex Hamiltonian.
method Rewriting PDE in dual stochastic control form, estimating optimal feedback control with neural network, approximating value function with neural networks.
result Improved estimation of PDE solution and its derivatives, especially the second derivative.
New neural network with RePU activation approximates smooth functions and their derivatives.
problem Approximating smooth functions and their derivatives with neural networks.
method Differentiable neural networks with RePU activation functions.
result Improved approximation error bounds for RePU-activated neural networks.
Artificial neural networks (ANNs) have very successfully been used in numerical simulations for a series of computational problems ranging from image classification/image recognition, speech recognition, time series analysis, game intelligence, and computational advertising to numerical approximations of partial differ…
We show that C0-fine approximation of convex functions by smooth (or real analytic) convex functions on Rd is possible in general if and only if d=1. Nevertheless, for d≥2 we give a characterization of the class of convex functions on Rd which can be approximated by real analytic (or just smoother) c…
Sharp bounds for approximating Sobolev functions by ridge functions and networks.
problem Approximating Sobolev functions with multivariate ridge functions and networks.
method Proving sharp upper and lower bounds for approximation order.
result Order of approximation asymptotically behaves as n−r/(d−ℓ). Corrected Monti's blow-up analysis for H-minimizing sets in Heisenberg group.
problem Blow-up analysis of H-minimizing sets in Heisenberg group with corrected partial differential equation.
method Revised Monti's results on blow-ups of H-perimeter minimizing sets in Hn and corrected the partial differential equation for the limit function. result Corrected the partial differential equation for the limit function of blow-ups in Heisenberg group.