arXiv research

Study on nodal components of random band-limited functions on surfaces, finding a universal law.

The paper improves confidence regions for band-limited functions using tighter norm bounds and majority voting.

We study the volume distribution of nodal domains of random band-limited functions on generic manifolds, and find that in the high energy limit a typical instance obeys a deterministic universal law, independent of the manifold. Some of the basic qualitative properties of this law, such as its support, monotonicity and…

The paper creates nonparametric confidence bands for band-limited functions.

This work uses sampling theory to analyze smoothness and error bounds of finite neural networks.

Band-limited training reduces resource usage without sacrificing accuracy.

In this paper, a nonparametric maximum likelihood (ML) estimator for band-limited (BL) probability density functions (pdfs) is proposed. The BLML estimator is consistent and computationally efficient. To compute the BLML estimator, three approximate algorithms are presented: a binary quadratic programming (BQP) algorit…

Wiatowski and Bölcskei, 2015, proved that deformation stability and vertical translation invariance of deep convolutional neural network-based feature extractors are guaranteed by the network structure per se rather than the specific convolution kernels and non-linearities. While the translation invariance result appli…

The paper improves nonparametric confidence bands for band-limited functions.

This paper presents a bias-variance tradeoff of graph Laplacian regularizer, which is widely used in graph signal processing and semi-supervised learning tasks. The scaling law of the optimal regularization parameter is specified in terms of the spectral graph properties and a novel signal-to-noise ratio parameter, whi…

We propose a novel class of Gaussian processes (GPs) whose spectra have compact support, meaning that their sample trajectories are almost-surely band limited. As a complement to the growing literature on spectral design of covariance kernels, the core of our proposal is to model power spectral densities through a rect…

Band-limited SAC improves learning efficiency and stability in simulated environments.

In data science, it is often required to estimate dependencies between different data sources. These dependencies are typically calculated using Pearson's correlation, distance correlation, and/or mutual information. However, none of these measures satisfy all the Granger's axioms for an "ideal measure". One such ideal…

Deep convolutional neural networks (CNNs) used in practice employ potentially hundreds of layers and $10$,$000$s of nodes. Such network sizes entail significant computational complexity due to the large number of convolutions that need to be carried out; in addition, a large number of parameters needs to be learned and…

The class of non-rigid registration methods proposed in the framework of PDE-constrained Large Deformation Diffeomorphic Metric Mapping is a particularly interesting family of physically meaningful diffeomorphic registration methods. PDE-constrained LDDMM methods are formulated as constrained variational problems, wher…

Study proper sampling for X-ray transforms on simple surfaces.

Compression of Neural Networks (NN) has become a highly studied topic in recent years. The main reason for this is the demand for industrial scale usage of NNs such as deploying them on mobile devices, storing them efficiently, transmitting them via band-limited channels and most importantly doing inference at scale. I…

Paper presents a unique method to recover signals from their bispectrum.

Developed a diffusion model on spherical data, addressing geometric and stochastic challenges.

GNNs outperform NNs in interpolating bandlimited functions on Euclidean cubes.

Deep convolutional neural networks have led to breakthrough results in numerous practical machine learning tasks such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction …

New method constrains CNN filter frequencies to improve robustness.

In this paper, we show synchronization for a group of output passive agents that communicate with each other according to an underlying communication graph to achieve a common goal. We propose a distributed event-triggered control framework that will guarantee synchronization and considerably decrease the required comm…

Random walk constructs Morse functions on surfaces.

Random permutations can offer faster convergence than with-replacement sampling for some functions.

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. B…

We study random Morse functions on a Riemann manifold $(M^m,g)$ defined as a random Gaussian weighted superpositions of eigenfunctions of the Laplacian of the metric $g$. The randomness is determined by a fixed Schwartz function $w$ and a small parameter $\varepsilon>0$. We first prove that as $\varepsilon\to 0$ the ex…

RST improves environmental time series classification accuracy using randomized B-spline trees.

Random Function Descent improves optimization in high dimensions.

We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of the form of nodes in neural networks. The universality result implies that the random ReLU features…

Learn low-degree functions with few random queries.

In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions from an interval adjusted to the target function, then randomly rotates the act…

The paper constructs random concave functions on the unit simplex.

We develop methods to learn dictionaries invariant under group symmetries, useful in cryo-EM and tracking.

New findings on how certain functionals behave in random variable spaces.

Positive-definite kernel functions are fundamental elements of kernel methods and Gaussian processes. A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a probability distribution. Another construction, which appears to have attracted less…

Gradient span algorithms show consistent progress in high dimensions.

Bayesian approach approximates probability functions of Gaussian mixtures.

Orthogonal random features approximate a Bessel kernel, offering sharper bounds than random Fourier features.

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that…

We study random knots, which we define as a triple of random periodic functions (where a random function is a random trigonometric series, \[f(θ) = \sum_{k=1}^\infty a_k \cos (k θ) +b_k (\sin k θ),\] with $a_k, b_k$ are independent gaussian random variables with mean $0$ and variance $σ(k)^2$ - our results will depend …

Recently, based on the idea of randomizing space theory, random convex analysis has been being developed in order to deal with the corresponding problems in random environments such as analysis of conditional convex risk measures and the related variational problems and optimization problems. Random convex analysis is …

HARFE approximates sparse additive functions using random features and ridge regression.

We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the m…

Random walk speed on Teichmüller space is a proper function.

Study predictive performance of linear regression with random functional covariates.

Introduces epistemic deep learning for better uncertainty estimation in neural networks.

New method optimizes hyperparameters for randomized algorithms like random feature regression.