arXiv research

Random matrix ensembles yield uniform distributions on manifolds.

New uniformity tester ensures consistent results across different samples.

Transforms uniform learners to work under arbitrary distributions efficiently.

New method upsamples sparse, non-uniform point clouds more accurately.

A groupoid $Ω\left( \mathcal{B} \right)$ called material groupoid is naturally associated to any simple body $\mathcal{B}$. The material distribution is introduced due to the (possible) lack of differentiability of the material groupoid. Thus, the inclusion of these new objects in the theory of material bodies opens th…

The theory of learning under the uniform distribution is rich and deep, with connections to cryptography, computational complexity, and the analysis of boolean functions to name a few areas. This theory however is very limited due to the fact that the uniform distribution and the corresponding Fourier basis are rarely …

Unified framework for non-uniform materials evolving over time.

Simpler, faster algorithm for uniformity testing in the shuffle model.

Develops uniform convergence guarantees for a broad class of risk functionals in supervised learning.

We propose a new setting for testing properties of distributions while receiving samples from several distributions, but few samples per distribution. Given samples from $s$ distributions, $p_1, p_2, \ldots, p_s$, we design testers for the following problems: (1) Uniformity Testing: Testing whether all the $p_i$'s are …

New findings on PAC learning and marginal distribution estimation.

New approach to adversarial robustness with non-uniform perturbations.

Uniform consistency proven for spatial distribution and depth estimators in any dimension.

UT module refines VAE latent space, improving disentanglement and interpretability.

We study the spherical cap packing problem with a probabilistic approach. Such probabilistic considerations result in an asymptotic sharp universal uniform bound on the maximal inner product between any set of unit vectors and a stochastically independent uniformly distributed unit vector. When the set of unit vectors …

Study uniform consistency in nonparametric mixture models and mixed regression.

New tester outperforms existing ones in uniformity testing.

Study sets limits for detecting a subhypergraph in uniform hypergraphs.

Concrete distribution properties examined on simplex.

Energy-efficient sampling for machine learning using magnetic tunnel junctions.

New method uses graphene transistors for efficient non-uniform random number generation.

The paper provides bounds on the CDF of a variable under nonstationary conditions.

NUTS mixing time scales as d^(1/4) for Gaussian distributions.

We study distribution testing with communication and memory constraints in the following computational models: (1) The {\em one-pass streaming model} where the goal is to minimize the sample complexity of the protocol subject to a memory constraint, and (2) A {\em distributed model} where the data samples reside at mul…

New framework improves learning across multiple distributions.

No free lunch theorems show all algorithms perform equally under uniform distribution.

We present a novel method for neural network quantization that emulates a non-uniform $k$-quantile quantizer, which adapts to the distribution of the quantized parameters. Our approach provides a novel alternative to the existing uniform quantization techniques for neural networks. We suggest to compare the results as …

New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.

Study spectral distribution of twisted Laplacian on high genus hyperbolic surfaces.

The paper introduces new uniformity and homogeneity concepts for Cosserat media.

Sharp bounds on uniform generalization errors in binary linear classification.

Interpolating label noise makes models vulnerable to adversarial attacks.

There has been significant study on the sample complexity of testing properties of distributions over large domains. For many properties, it is known that the sample complexity can be substantially smaller than the domain size. For example, over a domain of size $n$, distinguishing the uniform distribution from distrib…

Conformal Test Martingales can be 'blind' to significant changes in data distribution.

We introduce a new category of multivariate conditional generative models and demonstrate its performance and versatility in probabilistic time series forecasting and simulation. Specifically, the output of quantile regression networks is expanded from a set of fixed quantiles to the whole Quantile Function by a univar…

Different models of capital exchange among economic agents have been proposed recently trying to explain the emergence of Pareto's wealth power law distribution. One important factor to be considered is the existence of risk aversion. In this paper we study a model where agents posses different levels of risk aversion,…

Unique continuation property for measures in high dimensions.

Frequency bias affects neural network training on non-uniform data.

Algorithm improves online learning in adversarial bandits.

In this paper, we describe the Maximum Uniformity of Distribution (MUD) algorithm with the power-law nonlinearity. In this approach, we hypothesize that neural network training will become more stable if feature distribution is not too much skewed. We propose two different types of MUD approaches: power function-based …

We study here numerically the behavior of an ideal gas like model of markets having only one non-consumable commodity. We investigate the behavior of the steady-state distributions of money, commodity and total wealth, as the dynamics of trading or exchange of money and commodity proceeds, with local (in time) fluctuat…

Algorithm reduces regret in distributed kernel bandits with shared randomness.

In this paper, we develop the notion of entropy for uniform hypergraphs via tensor theory. We employ the probability distribution of the generalized singular values, calculated from the higher-order singular value decomposition of the Laplacian tensors, to fit into the Shannon entropy formula. We show that this tensor …

New sampler improves uniform sampling over convex bodies with fewer queries.

New bounds for agnostic learning with average smoothness.

Adaptive sampling improves graph diffusion models by maintaining uniform information speed.

This work optimizes alignment and uniformity of features on a hypersphere for better downstream performance.

Study shows uniform-time chaos propagation in mean field Langevin dynamics.