arXiv research

Maximum likelihood estimation fails to be well-posed in Gaussian process regression.

Corrects pseudo log-likelihood method issues in various applications.

We propose a robust estimator to improve maximum likelihood in probabilistic models.

We consider two connected aspects of maximum likelihood estimation of the parameter for high-dimensional discrete graphical models: the existence of the maximum likelihood estimate (mle) and its computation. When the data is sparse, there are many zeros in the contingency table and the maximum likelihood estimate of th…

Proposes a new approach to approximate maximum likelihood for complex models.

Paper presents a method for estimating Hawkes process parameters.

Invertibility conditions for observation-driven time series models often fail to be guaranteed in empirical applications. As a result, the asymptotic theory of maximum likelihood and quasi-maximum likelihood estimators may be compromised. We derive considerably weaker conditions that can be used in practice to ensure t…

A boosting method improves nonparametric density estimation without smoothing assumptions.

Machine learning should incorporate maximum likelihood for better estimation.

A new method improves text generation quality and diversity.

New approach resolves ambiguity in PPCA model's maximum likelihood estimation.

Paper quantifies label shift robustly.

We improve maximum likelihood for location estimation in finite samples.

Geometric approach solves maximum likelihood for Cauchy-like distributions.

Investigates numerical issues in GP interpolation parameter estimation.

We present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes maximum entropy principle and from standard maximum likelihood estimation.We demonstrate the LME principle BY deriving …

We develop a maximum penalized quasi-likelihood estimator for estimating in a nonparametric way the diffusion function of a diffusion process, as an alternative to more traditional kernel-based estimators. After developing a numerical scheme for computing the maximizer of the penalized maximum quasi-likelihood function…

Estimates GLMs robustly against label corruptions.

A new method speeds up quantum state estimation.

Geodesic descent optimizes likelihood in dually flat spaces.

New particle algorithms optimize latent variable models.

New method estimates latent gene expression factors without overlap with known confounders.

Efficiently estimates GEV distribution parameters using neural networks.

Proposes a guaranteed regularization method for maximum likelihood estimation using gauge symmetry in Kullback-Leibler divergence.

Paper proposes a method to estimate true positive proportion without knowing it.

This paper addresses the estimation of parameters of a Bayesian network from incomplete data. The task is usually tackled by running the Expectation-Maximization (EM) algorithm several times in order to obtain a high log-likelihood estimate. We argue that choosing the maximum log-likelihood estimate (as well as the max…

The maximum likelihood approach is adapted to the problem of estimation of drift and diffusion functions of stochastic processes from measured time series. We reconcile a previously devised iterative procedure [Kleinhans et al., Physics Letters A (346), 2005] and put the application of the method on a firm theoretical …

New estimator for tensor weights with improved bias.

Unified plug-in approach for estimating symmetric properties of distributions efficiently.

Improved MMD estimator for likelihood-free inference.

The EM algorithm is a novel numerical method to obtain maximum likelihood estimates and is often used for practical calculations. However, many of maximum likelihood estimation problems are nonconvex, and it is known that the EM algorithm fails to give the optimal estimate by being trapped by local optima. In order to …

Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.

New method for efficient maximum likelihood estimation of $p$-generalized probit regression.

A scalable method for estimating spatial data using VREML.

Using stochastic gradient search and the optimal filter derivative, it is possible to perform recursive (i.e., online) maximum likelihood estimation in a non-linear state-space model. As the optimal filter and its derivative are analytically intractable for such a model, they need to be approximated numerically. In [Po…

We consider the problem of sparse estimation in a factor analysis model. A traditional estimation procedure in use is the following two-step approach: the model is estimated by maximum likelihood method and then a rotation technique is utilized to find sparse factor loadings. However, the maximum likelihood estimates c…

A new method normalizes EBM training by introducing a learnable parameter.

The paper proposes a mixture model with segmentation for heterogeneous functional data.

Estimates log-likelihood of interacting particle systems using virtual particles.

Consistent estimator for mixtures of nonparametric elliptical distributions helps cluster analysis.

New method estimates Schrödinger bridges using ML techniques.

CMLE reduces spurious correlations in deep models.

Improved autoregressive models generate higher quality images and are more robust to noise.

MAXENT method outperforms ML in sparse data with specific prior correlations.

The MDL two-part coding $\textit{index of resolvability}$ provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. However, the bound does not apply to unpenalized maximum likelihood estimation or procedures with exceedingly small penalties. In this paper,…

Graphical lasso may fail to fit models when data points are insufficient.

Study uniform rates for estimating Gaussian mixtures without separation assumption.

Maximum likelihood (ML) estimation using Newton's method in nonlinear state space models (SSMs) is a challenging problem due to the analytical intractability of the log-likelihood and its gradient and Hessian. We estimate the gradient and Hessian using Fisher's identity in combination with a smoothing algorithm. We exp…