English
Related papers

Related papers: KALE Flow: A Relaxed KL Gradient Flow for Probabil…

200 papers

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence…

Machine Learning · Computer Science 2022-03-01 Parikshit Gopalan , Nina Narodytska , Omer Reingold , Vatsal Sharan , Udi Wieder

Kullback-Leibler (KL) divergence is one of the most important divergence measures between probability distributions. In this paper, we prove several properties of KL divergence between multivariate Gaussian distributions. First, for any two…

Information Theory · Computer Science 2023-01-24 Yufeng Zhang , Wanwei Liu , Zhenbang Chen , Ji Wang , Kenli Li

Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its…

Machine Learning · Computer Science 2025-03-05 Jiajun He , Wenlin Chen , Mingtian Zhang , David Barber , José Miguel Hernández-Lobato

This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ratio estimation (DRE). Both the KL-divergence and the IPMs…

Machine Learning · Computer Science 2022-02-01 Masahiro Kato , Masaaki Imaizumi , Kentaro Minami

We consider the maximum mean discrepancy ($\mathrm{MMD}$) GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized $\mathrm{MMD}$ GAN. We show that this flow provides a descent…

Machine Learning · Computer Science 2020-11-05 Youssef Mroueh , Truyen Nguyen

Flow-based generative models enjoy certain advantages in computing the data generation and the likelihood, and have recently shown competitive empirical performance. Compared to the accumulating theoretical studies on related score-based…

Machine Learning · Statistics 2025-06-30 Xiuyuan Cheng , Jianfeng Lu , Yixin Tan , Yao Xie

Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects, with applications in generative modeling for tasks in fields such as causal discovery, NLP, and…

Machine Learning · Computer Science 2026-04-13 Tiago da Silva , Eliezer de Souza da Silva , Diego Mesquita

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

Let $V_* : \mathbb{R}^d \to \mathbb{R}$ be some (possibly non-convex) potential function, and consider the probability measure $\pi \propto e^{-V_*}$. When $\pi$ exhibits multiple modes, it is known that sampling techniques based on…

Optimization and Control · Mathematics 2023-02-24 Carles Domingo-Enrich , Aram-Alexandre Pooladian

Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and…

Machine Learning · Computer Science 2026-04-02 Hoang-Chau Luong , Dat Ba Tran , Lingwei Chen

Consider the nonparametric logistic regression problem. In the logistic regression, we usually consider the maximum likelihood estimator, and the excess risk is the expectation of the Kullback-Leibler (KL) divergence between the true and…

Statistics Theory · Mathematics 2025-02-26 Atsutomo Yara , Yoshikazu Terada

Discrete normal distributions are defined as the distributions with prescribed means and covariance matrices which maximize entropy on the integer lattice support. The set of discrete normal distributions form an exponential family with…

Information Theory · Computer Science 2022-01-25 Frank Nielsen

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

Machine Learning · Statistics 2025-10-24 Zijun Gao , Yan Sun , Han Su

In reinforcement learning and imitation learning, an object of central importance is the state distribution induced by the policy. It plays a crucial role in the policy gradient theorem, and references to it--along with the related…

Machine Learning · Computer Science 2023-05-02 Gideon Freund , Elad Sarafian , Sarit Kraus

We pose the Kantorovich optimal transport problem as a min-max problem with a Nash equilibrium that can be obtained dynamically via a two-player game, providing a framework for approximating optimal couplings. We prove convergence of the…

Optimization and Control · Mathematics 2025-05-28 Lauren Conger , Franca Hoffmann , Ricardo Baptista , Eric Mazumdar

Sampling a target probability distribution with an unknown normalization constant is a fundamental challenge in computational science and engineering. Recent work shows that algorithms derived by considering gradient flows in the space of…

Machine Learning · Statistics 2024-03-12 Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Sebastian Reich , Andrew M Stuart

Gradient flows of the Kullback--Leibler (KL) divergence, such as the Fokker--Planck equation and Stein Variational Gradient Descent, evolve a distribution toward a target density known only up to a normalizing constant. We introduce new…

Machine Learning · Statistics 2026-02-09 Elias Hess-Childs , Dejan Slepčev , Lantian Xu

The problem of estimating the Kullback-Leibler divergence $D(P\|Q)$ between two unknown distributions $P$ and $Q$ is studied, under the assumption that the alphabet size $k$ of the distributions can scale to infinity. The estimation is…

Information Theory · Computer Science 2018-02-22 Yuheng Bu , Shaofeng Zou , Yingbin Liang , Venugopal V. Veeravalli

Maximum Likelihood Estimators (MLE) has many good properties. For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{\'e}r-Rao lower bound (efficiency bound), which is the minimum possible variance for…

Machine Learning · Statistics 2019-11-05 Song Liu , Takafumi Kanamori , Wittawat Jitkrittum , Yu Chen

Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed…

Statistics Theory · Mathematics 2025-06-06 Iosif Lytras , Sotirios Sabanis , Ying Zhang