arXiv research

Optimal mixtures of generative models outperform individual models on image datasets.

Paper establishes universal lower bounds and optimal rates for clustering sub-exponential mixture models.

Optimal transport for vector Gaussian mixtures improves efficiency and structure preservation.

The paper uses Gaussian mixture models for Bayesian networks and proposes an optimization algorithm.

Simplified explanation of ML for mixtures and OT.

Transformers can learn optimal regression mixtures efficiently.

NMDR estimates complex mixtures of distributions efficiently.

A novel optimization-based Gaussian mixture reduction method using composite transportation divergence.

Paper introduces risk-sensitive bandits with optimal arm mixtures.

The parsimonious Gaussian mixture models, which exploit an eigenvalue decomposition of the group covariance matrices of the Gaussian mixture, have shown their success in particular in cluster analysis. Their estimation is in general performed by maximum likelihood estimation and has also been considered from a parametr…

Bayesian Optimization improves data mixture selection for large language models.

Paper optimizes clustering for multi-layer networks and discrete mixtures.

Study proposes a new metric for comparing Gaussian mixtures in RKHS.

GAT-GMM improves GANs' performance in learning Gaussian mixture models.

Optimizes portfolios with GM returns using convex optimization.

The paper solves robust learning of Gaussian mixtures with nearly optimal guarantees.

Optimizes clustering in Gaussian mixtures with varying covariance matrices.

New algorithm learns permutations mixtures with optimal sample complexity.

A new method uses Mean Field Games to optimize mixture models of Bernoulli and categorical distributions.

MixMin finds optimal data mixtures for better model performance.

Mixture modeling is a general technique for making any simple model more expressive through weighted combination. This generality and simplicity in part explains the success of the Expectation Maximization (EM) algorithm, in which updates are easy to derive for a wide class of mixture models. However, the likelihood of…

EnEMF uses Epanechnikov kernel for high-dimensional filtering, improving accuracy and robustness.

This work explores the non-convex optimization in compressive learning and the performance of heuristics.

Motivated by problems in data clustering, we establish general conditions under which families of nonparametric mixture models are identifiable, by introducing a novel framework involving clustering overfitted \emph{parametric} (i.e. misspecified) mixture models. These identifiability conditions generalize existing con…

The learning of mixture models can be viewed as a clustering problem. Indeed, given data samples independently generated from a mixture of distributions, we often would like to find the {\it correct target clustering} of the samples according to which component distribution they were generated from. For a clustering pr…

Bayesian framework learns latent preference archetypes for many-objective optimization.

Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framework for variance reduction that enables the use of mixtures over predefined sampling distributions, which can naturally encode prior knowledg…

New algorithm clusters Gaussian mixtures with unknown covariance efficiently.

New framework shifts bandit algorithms from expected reward to preference metrics, optimizing mixtures of arms.

We consider the problem of learning the weighted edges of a balanced mixture of two undirected graphs from epidemic cascades. While mixture models are popular modeling tools, algorithmic development with rigorous guarantees has lagged. Graph mixtures are apparently no exception: until now, very little is known about wh…

New method uses dendrograms for better mixture model selection and clustering.

This paper optimizes Gaussian mixture model learning with optimal sampling complexity.

Improved sample efficiency for private learning of Gaussian mixtures.

The paper optimizes hyperplanes for binary classification in high-dimensional data with latent Gaussian mixtures.

We examine some differential geometric approaches to finding approximate solutions to the continuous time nonlinear filtering problem. Our primary focus is a new projection method for the optimal filter infinite dimensional Stochastic Partial Differential Equation (SPDE), based on the direct L2 metric and on a family o…

The paper optimizes estimating high-dimensional Gaussian mixtures without separation conditions.

Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For …

Boosting variational inference (BVI) approximates an intractable probability density by iteratively building up a mixture of simple component distributions one at a time, using techniques from sparse convex optimization to provide both computational scalability and approximation error guarantees. But the guarantees hav…

DUET optimizes LLM training data mixtures using feedback from unseen tasks.

New method improves Gaussian Mixture Model fitting speed.

New method estimates mixture distributions using stochastic mirror descent.

A new method for steering large agent populations efficiently.

New algorithm reduces regret in linear mixture SSPs without cost bounds.

New model generates data without mode collapse or mixture.

This paper studies identifiability and convergence behaviors for parameters of multiple types in finite mixtures, and the effects of model fitting with extra mixing components. First, we present a general theory for strong identifiability, which extends from the previous work of Nguyen [2013] and Chen [1995] to address…

Study uniform rates for estimating Gaussian mixtures without separation assumption.

Optimal classification rules control error rates in multiclass mixture models.

Optimizes mixture models without parametrizing distributions using tensor decomposition.