Paper studies equatorial concentration of measure in sphere immersions and submersions.
problem Equatorial concentration of measure in sphere immersions and submersions.
method Analyzes concentration of measure phenomena in the sphere.
result Describes an equatorial concentration of measure for minimal immersions and submersions.
We prove that an approximated version of the Brunn--Minkowski inequality with volume distortion coefficient implies a Gaussian concentration-of-measure phenomenon. Our main theorem is applicable to discrete spaces.
The study characterizes heat flow and concentration on directed graphs with a lower Ricci curvature bound.
problem Understanding heat flow and concentration on directed graphs with a specific curvature bound.
method Characterization via gradient estimate and transportation inequality for the heat semigroup.
result Concentration of measure inequality for directed graphs with positive Ricci curvature.
The paper offers a framework to analyze machine learning problems using concentration of measure.
problem Analyzing machine learning algorithms defined by implicit equations.
method Develops a concentration of measure framework to solve convex problems and implicit formulations.
result Provides precise estimations for the first moments of the solution, describing the behavior and performance of machine learning classifiers.
New local ID estimators based on data separability.
problem Estimating intrinsic dimensionality locally in multi-dimensional data.
method Local estimators based on concentration of measure.
result Empirical comparison with other ID estimators.
The paper generalizes product inequalities for random vectors and their applications.
problem Understanding concentration of measure for products of random vectors.
method Develops expressions for the concentration of functionals of random vectors based on product norms.
result Provides generalized Hanson-Wright inequalities and applications to random matrices.
Improved estimation of concentration using half-spaces for adversarial vulnerability.
problem Understanding the concentration of measure phenomenon and its impact on adversarial vulnerability.
method Extending Gaussian Isoperimetric Inequality to non-spherical Gaussian measures and arbitrary ℓ_p-norms, using half-spaces to estimate concentration.
result Proposed method finds tighter intrinsic robustness bounds, providing evidence against concentration as a cause of adversarial vulnerability.
Paper introduces information-constrained optimal transport, generalizing Talagrand's inequality.
problem Optimal transport problem with information constraints.
method Information constrained variation of optimal transport, using Marton's approach.
result Recovery of concentration of measure results and solution to Cover's open problem.
New study on No-U-Turn Sampler for accelerated mixing in Hamiltonian Monte Carlo.
problem Achieving accelerated convergence in Hamiltonian Monte Carlo.
method Combining concentration of measure and coupling analysis for mixing.
result Rigorous mixing guarantees for the No-U-Turn Sampler in certain Gaussian distributions.
New deficit functions link elliptic and parabolic inequalities, proving log Sobolev.
problem Proving log Sobolev inequality using deficit functions.
method Introducing two deficit functions, one elliptic and one parabolic, and showing their pointwise convergence and equations.
result Elliptic deficit converges to parabolic deficit, leading to an elliptic proof of log Sobolev inequality.
Study robust covariance estimation in large data with concentrated vectors.
problem Estimating robust covariance in large data with concentrated vectors.
method Fixed point of a contracting function using stable semi-metric and concentration of measure.
result Existence and uniqueness of robust estimator with evaluated limiting spectral distribution.
High-dimensional statistics advances in complex data domains.
problem Complex, rich datasets challenge traditional methods.
method Evolved to address sophisticated estimation and inference problems.
result Deepened connections with optimization, concentration, and information theory.
Many modern machine learning classifiers are shown to be vulnerable to adversarial perturbations of the instances. Despite a massive amount of work focusing on making classifiers robust, the task seems quite challenging. In this work, through a theoretical study, we investigate the adversarial risk and robustness of cl…
A new method approximates the Sliced-Wasserstein distance without random projections.
problem Efficiently approximating the Sliced-Wasserstein distance for machine learning applications.
method Utilizing the concentration of measure phenomenon to develop a deterministic approximation.
result The approximation error goes to zero as the dimension increases, under a weak dependence condition.
High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.
problem Why machine learning models achieve near-perfect accuracy in spectroscopic classification tasks without chemically meaningful features.
method Theoretical analysis grounded in the Feldman-Hajek theorem and concentration of measure, combined with specific experiments on synthetic and real fluorescence spectra.
result Infinitesimal distributional differences in high-dimensional spaces can lead to perfect separability, making models achieve near-perfect accuracy in spectroscopy.
Expanding on techniques of concentration of measure, we develop a quantitative framework for modeling liquidity risk using convex risk measures. The fundamental objects of study are curves of the form (ρ(λX))λ≥0, where ρ is a convex risk measure and X a random variable, and we call such a curve a \emph{liqu…
Quantum neural networks converge to Gaussian processes as they grow.
problem Understanding the convergence of quantum neural networks to Gaussian processes.
method Analyzing Haar random unitary and orthogonal deep QNNs, considering input states, measurement observables, and non-independence of unitary matrix entries.
result Quantum neural networks outputs converge to Gaussian processes in the limit of large Hilbert space dimension.
Deep models can't generate heavy-tailed samples well.
problem Understanding the limitations of deep generative models in generating samples with heavy tails.
method Unified framework using concentration of measure and convex geometry, Gromov-Levy inequality.
result Deep generative models are not universal generators and can only produce concentrated samples with light tails.
New bound improves on weighted majority vote risk estimation.
problem Improving risk estimation for weighted majority vote.
method Novel Chebyshev-Cantelli inequality and PAC-Bayes-Bennett inequality.
result New bounds improve on existing methods.
G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.
problem Creating high-accuracy binary neural networks with theoretical guarantees.
method Proposes a novel floating-point G-Net family with randomized binary embeddings and theoretical accuracy guarantees.
result Empirically, G-Net achieves almost 30% higher accuracy on CIFAR-10 compared to prior HDC models.
In this paper, I shall demonstrate that sufficiently high-dimensional closed positively-curved Riemannian manifolds are either diffeomorphic to a spherical space form, or isometric to a locally compact rank one symmetric space. This surprising classification of positively-curved Riemannian manifolds results from combin…
Next-gen reservoir computers fail to predict complex processes, highlighting need for better architectures.
problem Predicting complex, non-Markovian processes with recurrent neural networks.
method Lower bound from Fano's inequality and analysis of large probabilistic state machines.
result Next-generation reservoir computers have an error probability at least 60% higher than optimal for highly non-Markovian processes.
We define a Hamilton-Jacobi semigroup acting on continuous functions on a compact length space. Following a strategy of Bobkov, Gentil and Ledoux, we use some basic properties of the semigroup to study geometric inequalities related to concentration of measure. Our main results are that (1) a Talagrand inequality on a …
In this paper we propose and study a family of continuous wavelets on general domains, and a corresponding stochastic discretization that we call Monte Carlo wavelets. First, using tools from the theory of reproducing kernel Hilbert spaces and associated integral operators, we define a family of continuous wavelets by …
New inequality for ternary variables improves on existing measures.
problem Analyzing excess losses and weighted majority votes with ternary random variables.
method Developed a split-kl inequality and its PAC-Bayes extension.
result Outperforms existing inequalities in certain regimes.
New methods learn from single graphs, improving transductive node classification.
problem Statistical foundations of transductive learning for single graphs.
method Developed new concentration-of-measure tools for large graphs.
result Achieved optimal nonparametric rate of N−1/2 for single graph learning. We investigate the m-relative entropy, which stems from the Bregman divergence, on weighted Riemannian and Finsler manifolds. We prove that the displacement K-convexity of the m-relative entropy is equivalent to the combination of the nonnegativity of the weighted Ricci curvature and the K-convexity of the weig…
Paper estimates EOT maps for non-compactly supported measures with subGaussian target.
problem Estimating EOT maps between non-compactly supported measures.
method Uses bias-variance decomposition, T1-transport inequalities, and concentration of measure results.
result Shows error decay rates for different cases of subGaussian measures.
Quantum systems are viewed as emergent systems from the fundamental degrees of freedom. The laws and rules of quantum mechanics are understood as an effective description, valid for the emergent systems and specially useful to handle probabilistic predictions of observables. After introducing the geometric theory of Ha…
We prove near-tight concentration of measure for polynomial functions of the Ising model under high temperature. For any degree d, we show that a degree-d polynomial of a n-spin Ising model exhibits exponential tails that scale as exp(−r2/d) at radius r=Ω~d(nd/2). Our concentration radius is opti…
Nearly all Gaussian points in high dimensions lie on a common ellipsoid.
problem Finding an ellipsoid that fits a large set of Gaussian points in high dimensions.
method Analyzing a random set of Gaussian points and proving a bound on their concentration.
result The bound nearly confirms a conjecture about fitting Gaussian points to ellipsoids.
Study on volume of tubes and concentration in Riemannian geometry.
problem Understanding concentration loci in Riemannian manifolds and their relation to tube volumes.
method Provided a general formula for tube volumes, specialized to totally geodesic submanifolds, and investigated concentration loci.
result Explicitly proved concentration for codimension one cases and explored characterizations in Wasserstein and Box distances.
Fictitious play is a simple and widely studied adaptive heuristic for playing repeated games. It is well known that fictitious play fails to be Hannan consistent. Several variants of fictitious play including regret matching, generalized regret matching and smooth fictitious play, are known to be Hannan consistent. In …
We introduce a class of generalized relative entropies (inspired by the Bregman divergence in information theory) on the Wasserstein space over a weighted Riemannian or Finsler manifold. We prove that the convexity of all the entropies in this class is equivalent to the combination of the nonnegative weighted Ricci cur…
In this paper, we consider a concentration of measure problem on Riemannian manifolds with boundary. We study concentration phenomena of non-negative 1-Lipschitz functions with Dirichlet boundary condition around zero, which is called boundary concentration phenomena. We first examine relation between boundary concen…
New insights into spectral statistics of sample covariance matrix for stable linear systems.
problem Estimating high-dimensional stable state transition matrices from noisy data.
method Combining spectral theorem for non-Hermitian operators, concentration of measure, and perturbation theory.
result The spectral radius of the sample covariance matrix exhibits phase transitions in high dimensions.
Study improves convergence rates for GVI under prior misspecification.
problem Improving convergence rates for GVI under prior misspecification.
method Proves rates of convergence and robustness to prior misspecification in GVI framework.
result Establishes sufficient conditions for existence and uniqueness of GVI posteriors.
In this paper, we propose and study a Nyström based approach to efficient large scale kernel principal component analysis (PCA). The latter is a natural nonlinear extension of classical PCA based on considering a nonlinear feature map or the corresponding kernel. Like other kernel approaches, kernel PCA enjoys good mat…
We propose and study a multi-scale approach to vector quantization. We develop an algorithm, dubbed reconstruction trees, inspired by decision trees. Here the objective is parsimonious reconstruction of unsupervised data, rather than classification. Contrasted to more standard vector quantization methods, such as K-mea…
We study a model where one target variable Y is correlated with a vector X:=(X_1,...,X_d) of predictor variables being potential causes of Y. We describe a method that infers to what extent the statistical dependences between X and Y are due to the influence of X on Y and to what extent due to a hidden common cause (co…
NUTS mixing time scales as d^(1/4) for Gaussian distributions.
problem Improving the efficiency of the No-U-Turn Sampler (NUTS) for Gaussian distributions.
method Coupling argument leveraging geometric structure of Gaussian concentration, uniformity analysis of NUTS transitions.
result The mixing time of NUTS scales as d^(1/4) for Gaussian distributions, up to logarithmic factors.
We design new algorithms for the combinatorial pure exploration problem in the multi-arm bandit framework. In this problem, we are given K distributions and a collection of subsets V⊂2[K] of these distributions, and we would like to find the subset v∈V that has largest mean, whi…
We consider the optimization problem associated with training simple ReLU neural networks of the form x↦∑i=1kmax{0,wi⊤x} with respect to the squared loss. We provide a computer-assisted proof that even if the input distribution is standard Gaussian, even if the dime…
We treat the so-called scenario approach, a popular probabilistic approximation method for robust minmax optimization problems via independent and indentically distributed (i.i.d) sampling from the uncertainty set, from various perspectives. The scenario approach is well-studied in the important case of convex robust o…
Improved bounds for Monte Carlo Rademacher Averages using self-bounding functions.
problem Proving sharper concentration bounds for MCERA.
method Deriving new bounds through self-bounding functions and concentration of measure.
result Novel bounds depend on data-dependent quantities, improving over standard methods.
Improves generative models by using heavy-tailed noise in score matching.
problem High-dimensional limitations of Gaussian noise in generative models.
method Extended DSM to generalised normal distribution, relaxed key assumptions, developed iterative noise scaling algorithm.
result Heavy-tailed DSM leads to improved generative performance.
Investigates the impact of finite VC dimension on neural network approximation and learning.
problem The influence of VC dimension on neural network approximation and learning from samples.
method Analysis of high-dimensional geometry and statistical learning theory, focusing on VC dimension.
result Finite VC dimension is beneficial for uniform convergence of empirical errors but not for approximation of functions from a probability distribution.
The standard linear and logistic regression models assume that the response variables are independent, but share the same linear relationship to their corresponding vectors of covariates. The assumption that the response variables are independent is, however, too strong. In many applications, these responses are collec…