New α-divergence loss function improves neural density ratio estimation.
problem Optimization challenges in existing DRE methods, especially overfitting and high sample requirements.
method Derived α-divergence loss function (α-Div) for neural density ratio estimation. result The α-divergence loss function (α-Div) offers stable and effective optimization for DRE. A density ratio is defined by the ratio of two probability densities. We study the inference problem of density ratios and apply a semi-parametric density-ratio estimator to the two-sample homogeneity test. In the proposed test procedure, the f-divergence between two probability densities is estimated using a density-r…
Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.
problem Unified understanding of KL-divergence and IPMs.
method Unified representation via maximum likelihood density-ratio estimation (DRE).
result Unified form of IPMs and novel DRM metrics.
Divergence estimators based on direct approximation of density-ratios without going through separate approximation of numerator and denominator densities have been successfully applied to machine learning tasks that involve distribution comparison such as outlier detection, transfer learning, and two-sample homogeneity…
Rank-statistic method approximates f-divergences without density-ratio estimation.
problem Approximating f-divergences without explicit density-ratio estimation. method Mapping distribution rank histograms to discrete f-divergence and averaging over random projections. result The rank-statistic estimator is a lower bound of the true f-divergence and converges under mild conditions. Adapts RKHS methods to estimate density ratios with optimal error.
problem Estimating density ratios from limited data.
method Minimizes regularized Bregman divergence in RKHS, with Lepskii type parameter choice.
result Adaptive minimax optimal error rate for quadratic loss.
A new approach to model rejection using density ratios.
problem Improving model performance through selective prediction.
method Optimization of a loss's risk with φ-divergence regularization to find an idealized data distribution.
result Model rejection can be made by comparing the density ratio of the idealized distribution to the actual data distribution.
New method estimates velocity fields for minimizing f-divergences without overfitting.
problem Minimizing statistical discrepancies between target and particle distributions.
method Directly estimate velocity fields using interpolation techniques, proving consistency under mild conditions.
result Consistent estimators of velocity fields improve accuracy in applications like domain adaptation and missing data imputation.
A new method optimizes a generalized Kullback-Leibler divergence for better simulation-based inference.
problem Optimizing likelihood functions when they are only known implicitly.
method Optimizes a generalized Kullback-Leibler divergence that accounts for normalization constants in unnormalized distributions.
result Unified approach that combines Neural Posterior Estimation and Neural Ratio Estimation.
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio e…
Unified framework for robust, stable, and efficient density ratio estimation.
problem Density-chasm and support-chasm problems in density ratio estimation.
method Dequantified diffusion-Schrödinger bridge (D3RE) framework with DDBI and DSBI.
result Offers uniform approximation and bounded time scores in theory and empirical performance.
TRE improves density-ratio estimation for highly dissimilar densities.
problem Density-ratio estimation fails for significantly different densities.
method Telescoping density-ratio estimation (TRE) framework.
result TRE yields substantial improvements over existing methods for mutual information estimation.
The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior of the latent variable using Kullback Leibler (KL) divergence. Although the stan…
Proposes a new learning method for RBMs that combines strengths of forward and reverse KLD.
problem Underfitting and mode-collapse issues in RBM learning.
method Ratio divergence learning using target energy.
result Significantly outperforms other learning methods in energy function fitting, mode-covering, and stability.
Improved language models using ratio-matching and KL divergence.
problem Efficiently modeling discrete data with diffusion models.
method Introduced new theorems and a novel CTMC transition-rate matrix for ratio-matching and KL divergence.
result 10-15% improvement in perplexity and faster training steps.
Unified framework for estimating density ratios across multiple distributions.
problem Binary density ratio estimation for multiple distributions.
method Unified framework based on Bregman divergence minimization.
result Generalization of binary DRE methods to multiple distributions.
Riesz regression connects to density ratio estimation for causal inference.
problem Estimating average treatment effects in causal inference.
method Riesz regression as a signed density ratio and least-squares importance fitting.
result Riesz regression and DRE are equivalent, allowing transfer of DRE results.
The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the rela…
Paper connects rejection learning to Bhattacharyya divergence.
problem Learning models to abstain from predictions.
method Developed a link between rejection and thresholding different statistical divergences, focusing on Bhattacharyya divergence.
result Rejector obtained by joint ideal distribution corresponds to thresholding of skewed Bhattacharyya divergence.
Proposes a method to prevent overfitting in deep DRE models.
problem Overfitting in deep DRE models using empirical Bregman divergence.
method Introduces a non-negative correction for empirical Bregman divergence.
result The proposed method mitigates train-loss hacking and improves performance.
Unbiased methods for alpha-divergence minimization struggle in high dimensions.
problem The difficulty of unbiased alpha-divergence minimization in high dimensions.
method Signal-to-Noise Ratio (SNR) analysis of gradient estimators.
result The SNR of the gradient estimator worsens exponentially with dimensionality.
FORE evaluates occupancy ratios without requiring Bellman completeness.
problem Offline reinforcement learning occupancy ratio estimation.
method Fitted occupancy-ratio evaluation (FORE) using adjoint Bellman recursion.
result FORE achieves convergence in KL without Bellman completeness.
Unified view of LR and RP gradients explained via divergence theorem.
problem Explaining the nature and relationship of LR and RP gradients.
method First principles approach using divergence theorem.
result Characterization of all possible estimators combining LR and RP.
Unified framework for estimating density ratios in causal inference.
problem Estimating density ratios for causal inference is challenging due to instability and curse of dimensionality.
method Bregman-Riesz regression unifies three methods: Bregman divergences, probabilistic classification, and Riesz loss.
result Unified framework improves density ratio estimation in causal inference.
The problem of estimation error in portfolio optimization is discussed, in the limit where the portfolio size N and the sample size T go to infinity such that their ratio is fixed. The estimation error strongly depends on the ratio N/T and diverges for a critical value of this parameter. This divergence is the manifest…
New binary loss functions improve density ratio estimation accuracy.
problem Improving accuracy of density ratio estimators using binary classifiers.
method Characterized loss functions based on prescribed error measures in Bregman divergences.
result Novel loss functions prioritize accurate estimation of large density ratio values.
SRFE clarifies KL divergences without unifying learning frameworks.
problem Inductive biases of KL divergences and their limitations.
method Introducing SRFE, a log-moment-based functional of the likelihood ratio.
result SRFE recovers KL divergences as limits and reveals a mean-variance tradeoff.
Stable and consistent model alignment for language models without assuming human preference models.
problem Lack of statistical consistency in existing alignment methods.
method Relative density ratio optimization between preferred and mixture of preferred and non-preferred data distributions.
result Our approach achieves statistical consistency and stability, providing tighter convergence guarantees.
This work extends balancing to various simulation-based inference algorithms for more conservative posterior approximations.
problem Overconfident posterior approximations in simulation-based inference.
method Introduces a balanced version of neural posterior estimation and contrastive neural ratio estimation.
result Balanced versions tend to produce conservative posterior approximations on various benchmarks.
A new metric evaluates generative models by comparing real and generated samples.
problem Evaluating the quality of generative models.
method Relative Density Ratio (RDR) function, optimization on variational form of φ-divergence.
result The RDR function provides a clear, interpretable, and numerically stable evaluation metric.
Unified framework for debiased machine learning using Riesz representer and Bregman divergence.
problem Estimating causal and structural parameters in machine learning.
method Generalized Riesz regression for fitting Riesz representer via Bregman divergence minimization.
result Automatic covariate balancing and Neyman orthogonality properties for debiased estimation.
We propose a direct estimation method for Rényi and f-divergence measures based on a new graph theoretical interpretation. Suppose that we are given two sample sets X and Y, respectively with N and M samples, where η:=M/N is a constant value. Considering the k-nearest neighbor (k-NN) graph of Y in the j…
We present a framework to understand GAN training as alternating density ratio estimation and approximate divergence minimization. This provides an interpretation for the mismatched GAN generator and discriminator objectives often used in practice, and explains the problem of poor sample diversity. We also derive a fam…
We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent estimation methods such as noise-contrastive estimation, ratio matching, and sco…
New bounds for estimating partition functions under bounded f-divergence.
problem Estimating partition functions with limited sample access.
method Information-theoretic characterization using integrated coverage profile and f-divergences. result Sharp phase transitions in sample complexity under f-divergences. Paper introduces an online method for estimating the difference between two probability distributions.
problem Estimating the difference between two probability density functions using available data.
method Non-parametric online likelihood-ratio estimation using Pearson-divergence functional minimization.
result The proposed method provides efficient online updates and theoretical guarantees for performance.
Unified framework for DRO using OT with constraints.
problem Handling ambiguity in likelihood ratios and outcomes.
method Unified framework leveraging optimal transport with conditional moment constraints.
result Unified approach enables adversarial perturbation of likelihood ratios and outcomes.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
problem Improving the quality of generated samples in GANs.
method Discriminator Contrastive Divergence (DCD) method.
result Significant improvement in generation quality on synthetic and real-world data.
Replacing MSE with f-divergence in diffusion models improves robustness under data contamination.
problem Improving robustness of diffusion models under data contamination.
method Replacing MSE with f-divergence in diffusion models.
result Empirical improvement in performance under data contamination.
This work develops sampling methods for differential privacy using SHK geometry.
problem Approximating sampling for the exponential mechanism in differential privacy.
method Develops perturbation theory for SHK gradient flows and applies to differential privacy.
result Derives time-dependent Pure-DP guarantees and Approximate-DP certificates.
The paper improves QD policy ensembles using distribution ratio estimators.
problem Training diverse and high-quality reinforcement learning agents.
method Using Stein variational gradient descent and distribution ratio estimators.
result The method generates diverse and high-quality reinforcement learning agents.
Paper studies regularized KKL divergence for distributions with disjoint supports.
problem Inability of original KKL divergence to handle distributions with disjoint supports.
method Proposes a regularized variant of KKL divergence, derives bounds, and provides closed-form expression.
result Regularized KKL divergence is well-defined for all distributions and has finite-sample bounds.
Bregman divergences play a central role in the design and analysis of a range of machine learning algorithms. This paper explores the use of Bregman divergences to establish reductions between such algorithms and their analyses. We present a new scaled isodistortion theorem involving Bregman divergences (scaled Bregman…
Study post-hoc Learning to Defer using density-ratio losses.
problem Optimizing decision-making between models and experts.
method Density-ratio losses for post-hoc L2D scorers, derived from class-probability estimation.
result The approach recovers known results and introduces new connections to expert comparison and anomaly detection.
Estimates density ratio for two-sample comparison using tree models.
problem Comparing two distributions given i.i.d. observations.
method Additive tree models with balancing loss for density ratio estimation.
result Bayesian inference provides uncertainty quantification for density ratio.
The paper develops a method to model high-dimensional data with many variables and weak signals.
problem Modeling high-dimensional dependent data with many explanatory variables and low signal-to-noise ratio.
method Penalized regression for high-dimensional data, factor modeling of residuals, high-dimensional white noise testing, projected Principal Component Analysis.
result Established asymptotic properties of the proposed method for high-dimensional data.
The paper examines VI for overparameterized BNNs, revealing a trade-off between likelihood and KL terms.
problem Critical issue in mean-field VI training for overparameterized BNNs.
method Theoretical and empirical study of overparameterized two-layer BNNs using VI.
result A trade-off between likelihood and KL terms in overparameterized regime, with KL scaling crucial.
Extends likelihood ratio exponential families to analyze various optimization methods.
problem Analyzing optimization methods like rate-distortion and information bottleneck.
method Linking geometric mixture paths to exponential families and using hypothesis testing.
result Provides a common mathematical framework for understanding these methods.