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.
Generalizes randomized SVD for better matrix approximations using Gaussian vectors.
problem Computing accurate rank-k approximations of matrices with limited data.
method Extends randomized SVD to multivariate Gaussian vectors, incorporating prior knowledge and using Gaussian processes.
result Demonstrates improved accuracy in approximating matrices and Hilbert-Schmidt operators.
Orthogonal random features approximate a Bessel kernel, offering sharper bounds than random Fourier features.
problem Approximating Gaussian kernel efficiently for large datasets.
method Use of Haar orthogonal matrices to construct orthogonal random features and analyze their bias and variance.
result Orthogonal random features approximate a Bessel kernel, not the Gaussian kernel, with sharper bounds.
Gradient descent in Gaussian random fields helps understand high-dimensional optimization problems.
problem Understanding high-dimensional optimization problems in deep learning.
method Modeling loss functions as Gaussian random fields and analyzing gradient descent.
result Gradient descent's improved loss function distribution and moments are analyzed and shown to be asymptotically normal.
Bounds on Gaussian approximation for neural networks with novel smoothing techniques.
problem Approximating the distribution of wide random neural networks.
method Stein's method, Gaussian smoothing, Laplacian operators, Cameron-Martin space.
result First bounds on Gaussian approximation of wide random neural networks.
Gradient span algorithms show consistent progress in high dimensions.
problem Understanding consistent training progress in large machine learning models.
method Proving deterministic behavior of gradient span algorithms on Gaussian random functions.
result Gradient span algorithms have asymptotically deterministic behavior in high dimensions.
Proves new concentration inequalities for sub-gaussian and sub-exponential variables.
problem Understanding functions of independent random variables better.
method Sub-gaussian and sub-exponential conditions, Rademacher complexities, Lipschitz function classes.
result Extension of Rademacher complexities to unbounded sub-exponential distributions.
We study random Morse functions on a Riemann manifold ( M m , g ) (M^m,g) ( M m , g ) defined as a random Gaussian weighted superpositions of eigenfunctions of the Laplacian of the metric g g g . The randomness is determined by a fixed Schwartz function w w w and a small parameter ε > 0 \varepsilon>0 ε > 0 . We first prove that as ε → 0 \varepsilon\to 0 ε → 0 the ex…
This paper uses random Fourier features to simplify latent force models and convolved Gaussian processes.
problem Expensive covariance matrix calculation in latent force models due to double integrals.
method Approximates double integrals using random Fourier features to obtain simpler analytical expressions.
result Simplified analytical expressions for covariance functions, leading to faster computation.
Paper introduces a nonparametric functional graphical model for random functions.
problem Estimating probabilistic conditional independence in functional graphical models.
method Functional sufficient dimension reduction to relax Gaussian or copula Gaussian assumptions.
result Enhances estimation accuracy and retains probabilistic conditional independence.
Sharp comparison for sub-Gaussian random variables in convex order.
problem Comparing sub-Gaussian random variables in convex order.
method Proving dominance using moment generating functions and convex functions.
result Sharp comparison established between specific sub-Gaussian random variables.
Study Gaussian approximation for deep neural networks with random weights.
problem Understanding the distribution of deep neural networks with random weights.
method Established Gaussian approximation bounds in Wasserstein-1 norm.
result Convergence rates of order n − ( 1 / 6 ) L − 1 + ε n^{-({1}/{6})^{L-1} + ε} n − ( 1 / 6 ) L − 1 + ε for deep networks with proportional layer widths. We introduce a new functional measure of tail dependence for weakly dependent (asymptotically independent) random vectors, termed weak tail dependence function. The new measure is defined at the level of copulas and we compute it for several copula families such as the Gaussian copula, copulas of a class of Gaussian mi…
Study reveals three limiting regimes for neural network functionals.
problem Understanding the behavior of functionals of random neural networks.
method Central and non-central limit theorems, Hermite expansions, Diagram Formula, Stein-Malliavin techniques.
result Three distinct limiting regimes based on fixed points of covariance function.
New method estimates Gaussian vector functions more efficiently.
problem Estimating functions of Gaussian vectors with high dimensions.
method Combines randomized dimension reduction and PCA.
result Algorithm outperforms Monte Carlo method by a factor of d.
Paper introduces a new method for Gaussian Processes that improves prediction and hyper-parameter optimization.
problem Efficiently predicting unknown functions and optimizing hyper-parameters in Gaussian Processes.
method Sequential randomized low-rank matrix factorization for incremental predictions and hyper-parameter optimization.
result The proposed method outperforms existing approaches in terms of accuracy and computational efficiency.
Paper presents characteristic function of Tsallis q-Gaussian and its applications.
problem Modeling input quantities in measurement models using Tsallis q-Gaussians.
method Developed a characteristic function and proposed a numerical method for its inversion.
result Exact probability distribution of output quantities can be determined.
Random neural networks with ReLU activations are non-Gaussian processes.
problem Understanding the behavior of neural networks with random initialization and rectified linear units.
method Proving these networks are non-Gaussian processes and deriving their properties.
result These networks can converge to non-Gaussian processes under certain conditions.
We derive Gaussian approximations for random forest predictions using region-based stabilization.
problem Improving the accuracy of random forest predictions for Poisson process data.
method Region-based stabilization and Malliavin-Stein method for multivariate Gaussian approximation.
result Established Gaussian approximation bounds for random forest predictions under Poisson process.
New framework improves adversarial robustness certification for various perturbations.
problem Certifying robustness against adversarial attacks in deep learning models.
method Unified functional optimization approach with non-Gaussian smoothing noise for multiple types of attacks.
result Achieves better certification results and identifies key trade-offs between accuracy and robustness.
The paper proposes a Gaussian mixture model for Hilbert-space-valued data.
problem Challenges in characterizing probability measures for infinite-dimensional random objects.
method Gaussian mixture framework based on kernel mean embeddings.
result The proposed algorithm yields a dense class of approximations in infinite-dimensional spaces.
Deep Random Splines model neural activity data with better dimensionality.
problem Modeling neural population data with shape constraints.
method Deep neural network transforming Gaussian noise into spline parameters.
result Better dimensionality reduction of neural spiking activity.
Improved kernel ridge regression for large datasets using weighted random binning.
problem Efficiently approximating kernel matrices for large-scale datasets.
method Introduced weighted random binning features for locality sensitive hashing.
result Weighted random binning features generate Gaussian processes of any desired smoothness.
Standard sparse pseudo-input approximations to the Gaussian process (GP) cannot handle complex functions well. Sparse spectrum alternatives attempt to answer this but are known to over-fit. We suggest the use of variational inference for the sparse spectrum approximation to avoid both issues. We model the covariance fu…
Random Gaussian fields on 4D Riemannian manifolds with conformal invariance.
problem Characterizing and analyzing Gaussian fields on 4D Riemannian manifolds.
method Constructing and analyzing co-biharmonic Gaussian fields with covariance kernels defined by the Paneitz operator.
result Rigorous derivation of quantum Liouville measure for ∣ γ ∣ < 8 |γ|<\sqrt8 ∣ γ ∣ < 8 . Study of cosmic microwave background polarization using spin random fields.
problem Detecting deviations from Gaussianity and anisotropies in cosmic fields.
method Explicit formula for Lipschitz-Killing curvatures of spin spherical random fields.
result Coherent with asymptotic results, providing new metric expressions.
Study on random matrices in deep neural networks using Gaussian data.
problem Distribution of singular values in product of random matrices in deep learning.
method Free probability theory combined with standard techniques of random matrix theory.
result Justification for applying free probability theory to non-independent random data matrices.
The paper connects Riemannian Gaussian distributions to random matrix theory and diffusion kernels.
problem Analyzing Riemannian Gaussian distributions on symmetric spaces.
method Analytical computation of marginals using orthogonal and skew orthogonal polynomials, and diffusion kernels.
result Riemannian Gaussian distributions are random matrix types, and their probability density functions can be computed analytically.
The study proves Gaussian universality of deep random features learning.
problem Understanding the test error in deep random features learning.
method Proving Gaussian universality of test error in ridge regression and arbitrary convex losses.
result Sharp asymptotic formula for test error in ridge regression setting.
Extends Gaussian process theory to Banach spaces.
problem Extending Gaussian process theory to Banach spaces.
method Investigates the connection between Gaussian processes and Gaussian random elements in reproducing kernel Banach spaces.
result Characterizes positive definite functions that arise from covariance operators in Banach space setting.
We use matricial free energy to regularize autoencoders, producing Gaussian-like codes.
problem Generating Gaussian-like codes for autoencoders.
method Define a differentiable loss function based on singular values of the code matrix, minimizing matricial free energy.
result Minimizing matricial free energy results in Gaussian-like codes that generalize.
Deep random feature models are analyzed for their performance with exact asymptotic expressions.
problem Understanding the performance of deep random feature models.
method Established a novel universality result and used the convex Gaussian Min-Max theorem.
result Exact asymptotic expressions for the performance of deep random feature models are derived.
The paper develops a uniform function estimator in RKHS for regression.
problem Reconstructing functions from noisy data at random locations.
method Using reproducing kernel Hilbert spaces and Gaussian random fields.
result The estimator converges uniformly to the conditional expectation.
Develops a new method for nonlinear dimension reduction using random features.
problem Statistical challenges in generalizing Gaussian process-based latent variable models to non-Gaussian data.
method Random feature latent variable models (RFLVMs) that approximate nonlinear relationships with linear functions of random features.
result RFLVMs produce comparable results to state-of-the-art methods on various data types.
We consider the signed density of the extremal points of (two-dimensional) scalar fields with a Gaussian distribution. We assign a positive unit charge to the maxima and minima of the function and a negative one to its saddles. At first, we compute the average density for a field in half-space with Dirichlet boundary c…
New bounds for optimal transport using Gaussian processes and rate-distortion functions.
problem Finding bounds for entropic optimal transport with mutual information constraints.
method Lifting technique to construct a Gaussian process and applying the majorizing measure theorem.
result Maximum expected inner product is equivalent to a truncated integral involving the rate-distortion function.
New test detects sparse alternatives in Gaussian random fields.
problem Detecting sparse alternatives in Gaussian random fields.
method Ad-hoc Kac Rice formula for second maximum distribution, exact spacing test.
result Exact t t t -spacing test for high power in detecting sparse alternatives. Study on using random subspaces for ERM with various loss functions.
problem Improving learning accuracy with computational savings from random subspaces.
method Random subspaces of a hypothesis space, considering data-dependent subspaces.
result Unified analysis showing computational efficiency can be improved without performance loss.
Researchers explore gauge freedom in entropies of q q q -Gaussian measures.
problem Exploring the gauge freedom of entropies in q q q -Gaussian measures. method Introducing a refined q q q -logarithmic function to demonstrate gauge freedom. result Different escort expectations can lead to the same entropy but different relative entropies.
Proposes a method to ensure latent space of AutoEncoders is Gaussian without randomness.
problem Ensuring latent space of AutoEncoders is Gaussian without randomness.
method Directly optimize agreement between empirical distribution function and desired CDF for chosen properties.
result Ensures latent space of AutoEncoders is Gaussian without randomness.
This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.
problem Theoretical confidence parameter in GP-UCB increases with iterations, leading to large values.
method Introduced IRGP-UCB, a randomized variant of GP-UCB using a shifted exponential distribution for confidence parameters.
result IRGP-UCB achieves sub-linear regret without increasing the confidence parameter.
A new model for stock price fluctuations is proposed, based upon an analogy with the motion of tracers in Gaussian random fields, as used in turbulent dispersion models and in studies of transport in dynamically disordered media. Analytical and numerical results for this model in a special limiting case of a single-sca…
Multi-output Gaussian processes (MOGP) are probability distributions over vector-valued functions, and have been previously used for multi-output regression and for multi-class classification. A less explored facet of the multi-output Gaussian process is that it can be used as a generative model for vector-valued rando…
A simple geometrical proof shows that any target function can be found in a random network's neighborhood.
problem Finding any target function in a random network's neighborhood.
method Geometrical proof using a simple model of a high-dimensional sphere projected onto a low-dimensional subspace.
result High-dimensional geometry ensures that a uniform distribution over a sphere reduces to a Gaussian distribution with negligible covariances, enabling the presence of any target function in a random network's neighborhood.
Enhanced Gaussian process models accelerate optimization and posterior approximation.
problem Improving the accuracy and speed of Gaussian process models for optimization and inference.
method Introduces a random exploration step to classical GP-UCB algorithms, facilitating faster convergence.
result New algorithms achieve nearly optimal convergence rates and provide bounds for Hellinger distance.
A new method for LDA using randomized Kaczmarz improves accuracy for large datasets.
problem Efficiently performing LDA on large datasets.
method Randomized Kaczmarz method applied to linear discriminant analysis.
result The method achieves comparable accuracy to full data LDA.
Randomly biased data makes complex models as easy to learn as simple ones.
problem Learning complex models like multi-index and sparse Boolean functions.
method Introducing a small random shift in the first moment of the data distribution.
result Randomly biased data makes Gaussian single index models and sparse Boolean functions as easy to learn as linear functions.
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 δ δ and d d d .