arXiv research

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and covariance feature matching IPMs allow for stable training of GANs, which we will call M…

The paper uses moment matching method for pricing spread options under Lévy models.

The paper tackles matching a desired mean in causal systems through shift interventions.

In high dimensions, the mean and geometric median are nearly identical.

New MMD estimators detect differences in missing paired data.

A new method solves high-dimensional MFGs using particle-based flow matching.

Paper tackles model vulnerabilities by reconstructing training data.

This paper studies the optimality of kernel methods in high-dimensional data clustering. Recent works have studied the large sample performance of kernel clustering in the high-dimensional regime, where Euclidean distance becomes less informative. However, it is unknown whether popular methods, such as kernel k-means, …

A new algorithm estimates mean under varying user data sizes with local differential privacy.

We present a new implementation of anisotropic mean curvature flow for contour recognition. Our procedure couples the mean curvature flow of planar closed smooth curves, with an external field from a potential of point-wise charges. This coupling constrains the motion when the curve matches a picture placed as backgrou…

In real supervised learning scenarios, it is not uncommon that the training and test sample follow different probability distributions, thus rendering the necessity to correct the sampling bias. Focusing on a particular covariate shift problem, we derive high probability confidence bounds for the kernel mean matching (…

New bounds show BBVI's gradient variance matches SGD conditions, improving parameterization efficiency.

CW-Gen models improve probabilistic time series forecasting by incorporating prior information.

Boosting trees can test necessary conditions for regression model calibration.

Robust score matching improves parameter estimation in contaminated data.

Paper proves minimizing movements match smooth droplet flow in 3D.

Decentralized learning for matching markets with time-varying preferences.

ABae efficiently computes subset means with expensive predicates using stratified sampling.

Improves deep learning training by matching mini-batch distributions.

Study proves NN matching is equivalent to Riesz regression for debiased machine learning.

A new method for training diffusion models using likelihood matching.

The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has been very popular in machine learning due to its "Occam's razor" interpretation. Unfortunately, calculating the potentials in the maximum-entro…

Sharp inequalities for matrix means with unknown variance.

We consider two multi-armed bandit problems with $n$ arms: (i) given an $ε> 0$, identify an arm with mean that is within $ε$ of the largest mean and (ii) given a threshold $μ_0$ and integer $k$, identify $k$ arms with means larger than $μ_0$. Existing lower bounds and algorithms for the PAC framework suggest that both …

Method infers parameters in complex diffusion processes.

Runge-Kutta methods are the classic family of solvers for ordinary differential equations (ODEs), and the basis for the state of the art. Like most numerical methods, they return point estimates. We construct a family of probabilistic numerical methods that instead return a Gauss-Markov process defining a probability d…

Method learns statistics of return distributions via neural networks and maximum mean discrepancy.

Gradient matching with Gaussian processes is a promising tool for learning parameters of ordinary differential equations (ODE's). The essence of gradient matching is to model the prior over state variables as a Gaussian process which implies that the joint distribution given the ODE's and GP kernels is also Gaussian di…

We propose a novel procedure which adds "content-addressability" to any given unconditional implicit model e.g., a generative adversarial network (GAN). The procedure allows users to control the generative process by specifying a set (arbitrary size) of desired examples based on which similar samples are generated from…

A new method for generating samples without training, using smoothed score matching.

Simple private estimators for mean and covariance outperform existing methods.

Deep generative models can learn to generate realistic-looking images, but many of the most effective methods are adversarial and involve a saddlepoint optimization, which requires a careful balancing of training between a generator network and a critic network. Maximum mean discrepancy networks (MMD-nets) avoid this i…

We introduce an evolutionary algorithm called recombinator-$k$-means for optimizing the highly non-convex kmeans problem. Its defining feature is that its crossover step involves all the members of the current generation, stochastically recombining them with a repurposed variant of the $k$-means++ seeding algorithm. Th…

Enhances learning of structured distributions using nonlinear denoising score matching.

The conditional-mean barrier helps diagnose deterministic surrogates missing uncertainty.

Study robust mean estimation under coordinate-level corruptions using Hamming distance.

New calibration bands for various distributions improve testing for auto-calibration.

New algorithm for learning preferences in decentralized matching markets reduces regret to logarithmic levels.

The learning of domain-invariant representations in the context of domain adaptation with neural networks is considered. We propose a new regularization method that minimizes the discrepancy between domain-specific latent feature representations directly in the hidden activation space. Although some standard distributi…

A novel bandit problem with context-dependent rewards and blocking.

We introduce a toy probabilistic model to analyze job-matching processes in recent Japanese labor markets for university graduates by means of statistical physics. We show that the aggregation probability of each company is rewritten by means of non-linear map under several conditions. Mathematical treatment of the map…

We construct a new class of complete constant mean curvature surfaces in R^3. These are geometrically different than the surfaces constructed by Kapouleas' gluing technique. These are obtained by piecing together half-Delaunay surfaces to the truncations of minimal k-noids. The gluing techniques are new: the surfaces a…

We propose an estimator for the mean of a random vector in $\mathbb{R}^d$ that can be computed in time $O(n^4+n^2d)$ for $n$ i.i.d.~samples and that has error bounds matching the sub-Gaussian case. The only assumptions we make about the data distribution are that it has finite mean and covariance; in particular, we mak…

CO2 algorithm creates coresets for generic smooth divergences efficiently.

Proposes DWMD for better matching of hidden representations across domains.

The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+ε, for some $ε\in (0,1]$. Surprisingly, moments of order 2 (i.e., finite variance) are suffi…

The paper introduces a quantum state system to count perfect matchings in graphs.

Given a solution of the (backwards) Ricci flow one can construct a so called canonical soliton metric on space-time, introduced by E. Cabezas-Rivas and P. Topping. We observe that for a mean curvature flow within a (backwards) Ricci flow background, the space-time track of the mean curvature flow yields a canonical sol…