A new method inflates and deflates data manifolds to estimate densities without losing universality.
problem Density estimation on low-dimensional manifolds with non-Euclidean support.
method Inflation-deflation approach using Normalizing Flows with added noise.
result Exact estimation of densities on manifolds with sufficient conditions and Gaussian noise approximation.
ELF simplifies normalizing flows, making them more efficient and universal.
problem Computational inefficiency of normalizing flows.
method ELF introduces a simple, one-layer network with closed-form Lipschitz constants, combining the ease of residual flows with the performance of autoregressive flows.
result ELF is a provably universal density approximator, more efficient computationally and parameter-wise.
Deep belief networks can approximate any multivariate density with binary hidden units.
problem Approximating multivariate probability densities with binary hidden units.
method Sharp quantitative bounds on approximation error in terms of hidden units.
result Deep belief networks can approximate any multivariate density with binary hidden units under mild integrability requirements.
Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions. Their fl…
In this paper, we present a novel way to summarize the structure of large graphs, based on non-parametric estimation of edge density in directed multigraphs. Following coclustering approach, we use a clustering of the vertices, with a piecewise constant estimation of the density of the edges across the clusters, and ad…
Neural-g models mixtures of densities with flexibility and accuracy.
problem Accurately estimating prior densities in g-models. method Neural network with softmax output for valid probability densities.
result Neural-g captures various prior shapes including flat, heavy-tailed, and discontinuous.
Accurate approximations to density functionals have recently been obtained via machine learning (ML). By applying ML to a simple function of one variable without any random sampling, we extract the qualitative dependence of errors on hyperparameters. We find universal features of the behavior in extreme limits, includi…
Boosting variational inference (BVI) approximates an intractable probability density by iteratively building up a mixture of simple component distributions one at a time, using techniques from sparse convex optimization to provide both computational scalability and approximation error guarantees. But the guarantees hav…
o1Neuro neural network approximates complex functions and converges quickly.
problem Approximating complex functions and ensuring convergence in neural networks.
method Sparse indicator activation neurons, population and sample level convergence properties.
result o1Neuro achieves optimal model approximation and convergence with high probability.
Paper improves speech separation by using deep neural networks for more accurate density priors.
problem Improving the accuracy of source priors for independent vector analysis in speech separation.
method Estimating the derivative of speech density using deep neural networks to optimize performance indices.
result Neural network density priors outperform previous ones in convergence speed and SIR.
Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.
problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.
Conditional density estimation is a general framework for solving various problems in machine learning. Among existing methods, non-parametric and/or kernel-based methods are often difficult to use on large datasets, while methods based on neural networks usually make restrictive parametric assumptions on the probabili…
We show that the topological modular functor from Witten-Chern-Simons theory is universal for quantum computation in the sense a quantum circuit computation can be efficiently approximated by an intertwining action of a braid on the functor's state space. A computational model based on Chern-Simons theory at a fifth ro…
Extends neural network approximations to guarantee continuity of real-world learning tasks.
problem Guaranteeing continuity of real-world learning tasks given by conditional expectations.
method Establishing conditions on learning tasks that guarantee their continuity under a factorization of the data-generating process.
result Conditions guaranteeing the continuity of practically any derived learning task.
Squared families are a new model class derived from linear transformations, offering convenient properties and universal approximation.
problem Developing a new class of probability models that are easier to handle and have useful properties.
method Introducing squared families as families of probability densities obtained by squaring a linear transformation of a statistic, and showing their properties and applications.
result Squared families have convenient properties and can approximate target densities well.
Bi-Lipschitz flows approximate a wide range of distributions.
problem Characterizing the expressivity of bi-Lipschitz normalizing flows.
method Linking score regularity to transport map bi-Lipschitzness via probability flow ODE.
result Gaussian pullbacks induced by bi-Lipschitz variance-preserving transport maps are L1-dense among all probability densities. New neural networks learn mappings between probability measures and functions.
problem Learning mappings between Wasserstein space of probability measures and function spaces.
method Two types of neural networks: bin density and cylindrical approximation, are proposed and supported by universal approximation theorems.
result Accuracy and efficiency of mean-field neural networks in generalization error with various test distributions.
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and argue that having a flexible prior is beneficial to both sample generation and infer…
Moser Flow generates models for complex geometries on manifolds without ODE solvers.
problem Learning generative models for complex geometries like spheres and tori.
method Moser Flow is a new class of continuous normalizing flows that parameterizes the model density as the divergence of a neural network.
result Moser Flow achieves significant improvements in density estimation, sample quality, and training complexity over existing methods.
UNIPoint universally approximates point process intensities.
problem How to precisely describe the flexibility of point process models.
method Proof using Stone-Weierstrass Theorem, transfer functions, and recurrent neural networks.
result UNIPoint performs better than other models on synthetic and real-world datasets.
Softmax attention approximates complex functions and subsumes many known universal approximators.
problem Universal approximation of continuous sequence-to-sequence functions.
method Interpolation-based analysis of attention's internal mechanism, showing its ability to approximate ReLU functions.
result Softmax attention is a universal approximator for continuous sequence-to-sequence functions.
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…
New algorithms for efficient return distribution approximation in reinforcement learning.
problem Efficiently approximating unknown return distributions in reinforcement learning.
method Introduced novel distributional dynamic programming algorithms for arbitrary probabilistic reward mechanisms.
result Proved error bounds for the algorithms in Wasserstein and Kolmogorov--Smirnov distances.
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. We leverage neural networks as universal approximators of monotonic functions to build a parameterization of conditional cumulative distribution functions (CDFs). By the application of automatic differentiation with respect to response variables and then to parameters of this CDF representation, we are able to build bl…
Deep learning speeds spectral density estimation for large 2D/3D grids.
problem Computational challenges in estimating spectral densities for large grids.
method Deep learning neural network for spectral density estimation.
result Deep learning estimator is a universal approximator and faster than existing methods.
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).
We introduce Hyper-Conditioned Neural Autoregressive Flow (HCNAF); a powerful universal distribution approximator designed to model arbitrarily complex conditional probability density functions. HCNAF consists of a neural-net based conditional autoregressive flow (AF) and a hyper-network that can take large conditions …
A new neural network for efficient density estimation.
problem Efficient density estimation for high-dimensional data.
method Triangular neural network implementation of neural autoregressive flow (NAF).
result Achieves state-of-the-art bits-per-dimension indices on MNIST and CIFAR-10.
The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth. Here we consider the natural `dual' scenario for networks of bounded width and arbitrary depth. Precisely, let n be the number of inputs neurons, m be the number of output neurons, and let ρ be any nonaff…
New variational formula for Rényi divergences improves neural network estimation in high dimensions.
problem Estimating Rényi divergences in high-dimensional systems.
method Derive and apply a variational formula for Rényi divergences over various function spaces.
result Neural network estimators of Rényi divergences are consistent under certain conditions.
We investigate an algorithm named histogram transform ensembles (HTE) density estimator whose effectiveness is supported by both solid theoretical analysis and significant experimental performance. On the theoretical side, by decomposing the error term into approximation error and estimation error, we are able to condu…
CF-INNs can approximate any invertible function, resolving a long-standing problem.
problem Whether CF-INNs can approximate any invertible function.
method Demonstrated CF-INNs are universal approximators for invertible functions by showing a convenient criterion.
result CF-INNs are universal approximators for invertible 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
Generative models improved with smoothed score functions for better sample quality.
problem Improving generative models for better sample quality.
method Smoothed score functions based on factorial Gaussian kernels.
result Single noise level achieved 14.15 Fréchet inception distance on CIFAR-10.
Novel approach to financial derivatives pricing using rough path theory.
problem No-arbitrage conditions in financial markets necessitating precise integration methods.
method Developed a polynomial-based approximation class for rough path functionals, extending to non-geometric rough paths.
result Motivated a hypothesis for payoff functionals in financial markets, facilitating analysis.
Transformers enable in-context learning with guarantees for a wide range of tasks.
problem How to enable in-context learning with transformers for various tasks.
method Developed a universal approximation theory integrating Barron's function approximation with transformer capabilities.
result Transformers can approximate any target function with vanishingly small risk using a few in-context examples.
Framework for universal graph function approximators outperforms existing methods.
problem Graph classification and separation of graph classes.
method Inspired by persistent homology, dependency parsing, and multivalued functions, the framework constructs universal approximators on graph isomorphism classes.
result Achieves state-of-the-art performance on four graph datasets.
Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning. Despite its remarkable empirical performance, there are limited theoretical studies on the statistical properties of GANs. This paper provides approximation and statistical guarantees of GANs for the estimation of data distri…
Quantum neural networks can approximate noisy functions accurately.
problem Approximating noisy functions with quantum neural networks.
method Universal approximation theorem with error bounds for noisy quantum neural networks.
result Quantum neural networks can approximate noisy functions with precise error bounds.
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.
Paper analyzes neural network models for sub-Gaussian distributions, proving approximation and generalization abilities.
problem Estimating unknown distributions from i.i.d. observations using neural network models.
method Score-based neural network generative models (SGMs) with specific network architectures and stopping strategies.
result SGMs can approximate scores with high accuracy and achieve nearly optimal convergence rates under mild assumptions.
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.
We analyze the constituents stocks of the Dow Jones Industrial Average (DJIA30) and the Standard & Poor's 100 index (S&P100) of the NYSE stock exchange market. Surprisingly, we discover the data collapse of the histograms of the DJIA30 price fluctuations and of the S&P100 price fluctuations to the universal non-paramet…
MLPs can approximate any function in context, challenging the importance of in-context universality.
problem Understanding why transformers are more effective than classical models.
method Proved MLPs with trainable activation functions are universal in context.
result Transformer success is likely due to factors other than in-context universality.
Unified theorem for deep and shallow joint-equivariant machines.
problem Universal approximation of joint-equivariant machines.
method Constructive universal approximation theorem based on ridgelet transform.
result Unified approximation of deep and shallow networks.
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. 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.