Maximum likelihood training improves the performance of score-based diffusion models.
problem Training score-based diffusion models with maximum likelihood.
method Trained by minimizing a weighted combination of score matching losses, with a specific weighting scheme that bounds negative log-likelihood.
result Maximum likelihood training improves the log-likelihood of score-based diffusion models across multiple datasets.
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…
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from co…
Noise-Contrastive Estimation improves efficiency for estimating log-likelihood of complex point processes.
problem Estimating log-likelihood of complex multivariate point processes is computationally expensive.
method Noise-Contrastive Estimation adapted for multivariate point processes, with provable guarantees.
result Our method achieves similar log-likelihood with fewer evaluations and less time.
Enhances VAEs for sharper image synthesis.
problem Blurriness in generated images from VAEs.
method Integrates a downscaled version of the original image into the VAE framework and uses it as input to the decoder.
result Improves FID score in image synthesis while maintaining similar log-likelihood performance.
We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds maximizes the Bayesian marginal likelihood. This provides an alternative explanatio…
Separable losses are inconsistent for structured prediction models.
problem Inconsistency of separable losses in structured prediction models.
method Analysis of separable negative log-likelihood losses for structured prediction.
result Separable losses are not Bayes consistent and may not predict the most probable structure.
Improved estimation for imbalanced data using log odds correction and optimal sampling.
problem Parameter estimation with nonuniform negative sampling for imbalanced data.
method Derive asymptotic distribution of IPW estimator, derive optimal sampling probability, propose likelihood-based estimator.
result Improved estimator has the smallest asymptotic variance.
We consider the finite sample properties of the regularized high-dimensional Cox regression via lasso. Existing literature focuses on linear models or generalized linear models with Lipschitz loss functions, where the empirical risk functions are the summations of independent and identically distributed (iid) losses. T…
Quantum machine learning uses quantum cross entropy to minimize loss, but measurement loss affects this process.
problem Quantum machine learning's loss minimization through cross entropy is affected by measurement outcomes.
method Defined quantum cross entropy, proved its lower bounds, and investigated its relation to quantum fidelity and likelihood.
result Quantum cross entropy is lower-bounded by negative log-likelihood when derived from quantum data, but measurement outcomes can cause loss.
Invertible DenseNets improve model efficiency and performance.
problem Improving model efficiency and performance in neural networks.
method Enforcing invertibility in DenseNets by satisfying the Lipschitz constraint and proposing a learnable concatenation.
result i-DenseNets outperform Residual Flows in negative log-likelihood on various datasets.
By exploiting the property that the RBM log-likelihood function is the difference of convex functions, we formulate a stochastic variant of the difference of convex functions (DC) programming to minimize the negative log-likelihood. Interestingly, the traditional contrastive divergence algorithm is a special case of th…
Partition Tree estimates conditional densities for mixed continuous and categorical variables.
problem Estimating conditional densities for mixed data types.
method Tree-based framework modeling conditional distributions as piecewise-constant densities on adaptive partitions, minimizing conditional negative log-likelihood.
result Improved probabilistic prediction compared to CART-style trees and state-of-the-art methods.
DNLL loss improves deep LDA accuracy and consistency.
problem Pathological solutions in unconstrained Deep LDA.
method Introducing Discriminative Negative Log-Likelihood (DNLL) loss.
result Deep LDA trained with DNLL produces clean latent spaces and better calibrated probabilities.
We consider log-supermodular models on binary variables, which are probabilistic models with negative log-densities which are submodular. These models provide probabilistic interpretations of common combinatorial optimization tasks such as image segmentation. In this paper, we focus primarily on parameter estimation in…
ELU algorithm improves on EM for over-specified Gaussian mixtures.
problem Slow convergence of EM in over-specified Gaussian mixtures.
method Developed ELU algorithm for two-component mixtures, combining exponential location update and gradient descent.
result ELU converges to final statistical radius after logarithmic iterations, resolving open question.
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the Kullback-Leibler divergence that allows understanding methods that penalize the …
Paper improves likelihood estimation for discrete distributions.
problem Computing profile maximum likelihood for discrete distributions.
method New bounds on Bethe and Sinkhorn permanents for low rank matrices.
result Achieves an approximation factor of exp(-O(sqrt(n) log n)) in polynomial time.
PACMAN provides bounds for classification tasks considering accuracy vs. negative log-loss mismatch.
problem Mismatch between accuracy and negative log-loss in classification tasks.
method Point-wise PAC approach over generalization gap, using likelihood ratio and concentration inequalities.
result PACMAN provides point-wise PAC bounds for the generalization problem.
Proposes a deep neural network for event intensity estimation.
problem Modeling irregular event sequences with historical dependencies.
method Non-parametric deep neural network with multi-channel RNN and fake event epochs.
result Outperforms state-of-the-art baselines on model fitting tasks.
Corrects pseudo log-likelihood method issues in various applications.
problem Log-likelihood function unbounded issues in pseudo log-likelihood methods.
method Provided a counterexample and corrected algorithms in previous literature.
result Ensured well-definedness of maximum pseudo log-likelihood estimation.
Test log-likelihood comparisons can be misleading.
problem Misinterpretation of test log-likelihood in model comparison.
method Simple examples of model comparison and forecast accuracy.
result Test log-likelihood does not always correlate with model accuracy.
GBHT uses gradient boosting for density estimation with theoretical guarantees.
problem Density estimation for unsupervised learning.
method Gradient Boosting Histogram Transform (GBHT) with Negative Log Likelihood loss.
result GBHT achieves faster convergence rates and better performance than base learners in density estimation.
In this paper we revisit the weighted likelihood bootstrap, a method that generates samples from an approximate Bayesian posterior of a parametric model. We show that the same method can be derived, without approximation, under a Bayesian nonparametric model with the parameter of interest defined as minimising an expec…
Active-set algorithm improves Cox regression for shape-restricted covariates.
problem Improving Cox regression for shape-restricted covariates.
method Shape-restricted inference using active-set optimization for spline basis expansion.
result Active-set algorithm produces accurate linear covariate effect estimates.
A new VIS approach improves log-likelihood estimation in latent variable models.
problem Challenges in achieving high log-likelihood with VI for complex posterior distributions.
method Uses forward χ2 divergence to optimize proposal distribution for better log-likelihood estimation. result Consistently outperforms state-of-the-art baselines in log-likelihood and parameter estimation.
wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.
problem Improving reasoning in diffusion-based large language models through RL.
method wd1: ratio-free policy optimization using weighted log-likelihood.
result wd1 outperforms diffusion-based GRPO while requiring lower computational cost.
We empirically investigate the (negative) expected accuracy as an alternative loss function to cross entropy (negative log likelihood) for classification tasks. Coupled with softmax activation, it has small derivatives over most of its domain, and is therefore hard to optimize. A modified, leaky version is evaluated on…
Study reveals structure of local minima in GMMs, identifying key cluster centers.
problem Identifying optimal cluster centers in non-convex GMM landscapes.
method Analyzing the negative log-likelihood function of GMMs in the population limit.
result Local minima share a common structure that partially identifies true cluster centers.
IBS efficiently estimates log-likelihood without bias.
problem Estimating log-likelihood for complex models.
method Inverse Binomial Sampling (IBS) for efficient, unbiased estimation.
result IBS produces lower error in estimated parameters and maximum log-likelihood values.
New method optimizes clustering with better log-likelihood landscape.
problem Nonconvex log-likelihood optimization in model-based clustering.
method Entropic optimal transport loss for Sinkhorn-EM algorithm.
result New loss function avoids spurious local optima.
New method calculates DMN log-likelihood faster.
problem Precise and fast computation of DMN log-likelihood.
method Derived a closed form expression using gamma function properties.
result Closed form calculation is faster with same accuracy.
Log-concavity proven for multinomial likelihoods under specific constraints.
problem Log-concavity of multinomial likelihoods under interval censoring constraints.
method Proved log-concavity by showing M-convex subsets of the discrete simplex.
result Likelihood function is completely log-concave.
Novel neural likelihood ratio estimation for negative data in particle physics.
problem Estimating likelihood ratios with negative probability densities and weights.
method Introducing a novel loss function and a new model architecture based on signed mixture models.
result Demonstrated improved estimation on a real-world example from particle physics.
This work investigates power laws in deep neural network ensembles and predicts their performance.
problem Understanding the performance of deep neural network ensembles and their optimal structure.
method Investigated the behavior of negative log-likelihood (CNLL) of a deep ensemble as a function of ensemble size and member network size, identifying power law dependencies.
result One large network may perform worse than an ensemble of several medium-size networks, known as a memory split.
Gaussian Process Factor Analysis (GPFA) has been broadly applied to the problem of identifying smooth, low-dimensional temporal structure underlying large-scale neural recordings. However, spike trains are non-Gaussian, which motivates combining GPFA with discrete observation models for binned spike count data. The dra…
PSO optimizes model parameters in nonstandard distributions.
problem Estimating model parameters in nonstandard distributions using existing algorithms.
method Particle Swarm Optimization (PSO) as an alternative optimization routine.
result PSO produces more optimal or convergent results than existing algorithms.
The Restricted Boltzmann Machines (RBM) can be used either as classifiers or as generative models. The quality of the generative RBM is measured through the average log-likelihood on test data. Due to the high computational complexity of evaluating the partition function, exact calculation of test log-likelihood is ver…
The paper analyzes LASSO penalization for high-dimensional Beta regression models.
problem Theoretical analysis of LASSO in high-dimensional Beta regression.
method Non-convexity handling through a neighborhood framework, debiasing for confidence intervals, proximal gradient algorithm.
result Non-asymptotic bound on ℓ1-error of stationary points. Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires the intractable partition function. Annealed importance sampling (AIS) is widely used to estimate MRF partition functions, and often yields quite accurate results. However, AIS is prone to ov…
A new method normalizes EBM training by introducing a learnable parameter.
problem Training energy-based models with maximum likelihood is challenging due to intractable normalisation constants.
method Proposes a self-normalised log-likelihood (SNL) objective that introduces a learnable parameter representing the normalisation constant.
result The SNL objective is a lower bound of the log-likelihood and can be directly optimised using stochastic gradient techniques.
We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score. Density estimators have been widely used for unsupervised anomaly detection. By the recent advance of deep learning, the density estimation performance has been greatly i…
Learning RBMs using standard algorithms such as CD(k) involves gradient descent on the negative log-likelihood. One of the terms in the gradient, which involves expectation w.r.t. the model distribution, is intractable and is obtained through an MCMC estimate. In this work we show that the Hessian of the log-likelihood…
Survival regression method improves log-likelihood scores.
problem Improper scoring rules in survival regression models.
method SurvivalMonotonic-net (SuMo-net) with monotonic neural networks.
result SuMo-net achieves state-of-the-art log-likelihood scores.
Improved Gaussian process regression with tighter log marginal likelihood bounds.
problem Improving predictive performance in Gaussian process regression models.
method Lower bound on log marginal likelihood using conjugate gradients.
result Improved predictive performance compared to other conjugate gradient based approaches.
In this short note we provide an unbiased multilevel Monte Carlo estimator of the log marginal likelihood and discuss its application to variational Bayes.
We consider Bayesian inference when only a limited number of noisy log-likelihood evaluations can be obtained. This occurs for example when complex simulator-based statistical models are fitted to data, and synthetic likelihood (SL) method is used to form the noisy log-likelihood estimates using computationally costly …
Likelihood-based generative models are the backbones of lossless compression due to the guaranteed existence of codes with lengths close to negative log likelihood. However, there is no guaranteed existence of computationally efficient codes that achieve these lengths, and coding algorithms must be hand-tailored to spe…