arXiv research

New method optimizes clustering with better log-likelihood landscape.

Geodesic descent optimizes likelihood in dually flat spaces.

Unified approach for sequence design combining likelihood-free inference and black-box optimization.

Optimizing full likelihoods adapts loss scales and shapes for robust modeling.

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelih…

Deep Gaussian Processes improve likelihood-free inference for complex distributions.

Poisson likelihood models have been prevalently used in imaging, social networks, and time series analysis. We propose fast, simple, theoretically-grounded, and versatile, optimization algorithms for Poisson likelihood modeling. The Poisson log-likelihood is concave but not Lipschitz-continuous. Since almost all gradie…

In this article we use rate-distortion theory, a branch of information theory devoted to the problem of lossy compression, to shed light on an important problem in latent variable modeling of data: is there room to improve the model? One way to address this question is to find an upper bound on the probability (equival…

Bayesian optimization improves by focusing on outputs with the likelihood ratio method.

Sparse modeling improves portfolio optimization by reducing errors in complex market systems.

Proposes a method to optimize neural network initialization using marginal likelihood maximization.

Optimally tackles covariate shift in RKHS-based nonparametric regression.

A fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions. Frequently, these nominal distributions are themselves estimated from data, which makes them susceptible to estimation errors. We thus propose to replace each…

Recently there has been sustained interest in modifying prediction algorithms to satisfy fairness constraints. These constraints are typically complex nonlinear functionals of the observed data distribution. Focusing on the path-specific causal constraints proposed by Nabi and Shpitser (2018), we introduce new theoreti…

The likelihood function is a fundamental component in Bayesian statistics. However, evaluating the likelihood of an observation is computationally intractable in many applications. In this paper, we propose a non-parametric approximation of the likelihood that identifies a probability measure which lies in the neighbor…

Simplified explanation of ML for mixtures and OT.

Directly estimates Fisher score for likelihood maximization.

Develops likelihood-based methods for trawl processes, improving forecasting accuracy.

Efficient Bayesian decision-making with intractable likelihoods.

New framework trains Schrödinger Bridge models using SDEs for generative tasks.

New method boosts BOED using SBI and neural likelihood.

A new method extends Bayesian optimization to more models and utilities.

This study benchmarks likelihood-free inference methods for models with heavy-tailed or discrete data.

A new method for experimental design focuses on predicting downstream quantities of interest.

Optimal selective classification using likelihood ratios improves model reliability.

The MAP estimate's log-likelihood sub-optimality is hard to bound in general.

wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.

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

This work optimizes statistical inference with neural networks for high-energy physics data.

Dimension reduction and variable selection are performed routinely in case-control studies, but the literature on the theoretical aspects of the resulting estimates is scarce. We bring our contribution to this literature by studying estimators obtained via L1 penalized likelihood optimization. We show that the optimize…

Unified framework for unlearning in diffusion models using KL divergence and likelihood constraints.

Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function, most of the existing inference methods optimize the simulator parameters through a handcrafted iterative procedure tha…

Innovative game theory approach optimizes survival analysis metrics.

Normalizing flows optimize Jacobian determinant for unique likelihood objective.

Optimizes AIS hyperparameters for efficient marginal likelihood estimation.

We investigate the problem of semi-parametric maximum likelihood under constraints on summary statistics. Such a procedure results in a discrete probability distribution that maximises the likelihood among all such distributions under the specified constraints (called estimating equations), and is an approximation to t…

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…

Optimizes MMD learning for generative models with theoretical guarantees.

New particle algorithms optimize latent variable models.

Most successful machine intelligence systems rely on gradient-based learning, which is made possible by backpropagation. Some systems are designed to aid us in interpreting data when explicit goals cannot be provided. These unsupervised systems are commonly trained by backpropagating through a likelihood function. We i…

A new method speeds up quantum state estimation.

Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likelihood-free, as their forward map has to be numerically approximated by an ODE solver. This, however, is not a fundamental constraint but jus…

The NL score optimizes speaker recognition tasks.

Maximum likelihood training improves the performance of score-based diffusion models.

We study the parameter estimation problem in mixture models with observational nonidentifiability: the full model (also containing hidden variables) is identifiable, but the marginal (observed) model is not. Hence global maxima of the marginal likelihood are (infinitely) degenerate and predictions of the marginal likel…

This paper optimizes subsampling for large datasets using Poisson distribution.

MINIMALIST maximizes mutual information for likelihood estimation from simulated data.

Investigates numerical issues in GP interpolation parameter estimation.