English
Related papers

Related papers: Shifted Composition III: Local Error Framework for…

200 papers

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

Unsupervised learning of disentangled representations involves uncovering of different factors of variations that contribute to the data generation process. Total correlation penalization has been a key component in recent methods towards…

Machine Learning · Computer Science 2020-01-01 Yijun Xiao , William Yang Wang

We propose a novel analysis framework for non-descent-type optimization methodologies in nonconvex scenarios based on the Kurdyka-Lojasiewicz property. Our framework allows covering a broad class of algorithms, including those commonly…

Optimization and Control · Mathematics 2024-06-05 Junwen Qiu , Bohao Ma , Xiao Li , Andre Milzarek

We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple…

Machine Learning · Computer Science 2020-07-14 Sebastian Claici , Mikhail Yurochkin , Soumya Ghosh , Justin Solomon

We propose and analyze a class of adaptive sampling algorithms for multimodal distributions on a bounded domain, which share a structural resemblance to the classic overdamped Langevin dynamics. We first demonstrate that this class of…

Machine Learning · Computer Science 2024-11-26 Björn Engquist , Kui Ren , Yunan Yang

To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined…

Machine Learning · Computer Science 2018-04-05 Boris Belousov , Jan Peters

Distributed learning of probabilistic models from multiple data repositories with minimum communication is increasingly important. We study a simple communication-efficient learning framework that first calculates the local maximum…

Machine Learning · Statistics 2014-10-13 Qiang Liu , Alexander Ihler

Discrete diffusion models have recently gained significant prominence in applications involving natural language and graph data. A key factor influencing their effectiveness is the efficiency of discretized samplers. Among these,…

Machine Learning · Computer Science 2025-11-03 Yuchen Liang , Yingbin Liang , Lifeng Lai , Ness Shroff

In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a…

Information Theory · Computer Science 2024-09-24 Zijian Yang , Vahe Eminyan , Ralf Schlüter , Hermann Ney

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical mechanics, in…

The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension…

Machine Learning · Statistics 2025-09-05 Yifan Chen , Xiaoou Cheng , Jonathan Niles-Weed , Jonathan Weare

We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$. We prove a convergence guarantee in Kullback-Leibler (KL) divergence assuming $\nu$ satisfies a log-Sobolev…

Data Structures and Algorithms · Computer Science 2022-03-04 Santosh S. Vempala , Andre Wibisono

In this paper, we investigate a continuous time version of the Stochastic Langevin Monte Carlo method, introduced in [WT11], that incorporates a stochastic sampling step inside the traditional over-damped Langevin diffusion. This method is…

Machine Learning · Statistics 2023-01-10 Marelys Crespo Navas , Sébastien Gadat , Xavier Gendre

We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergence when $\nu$…

Machine Learning · Statistics 2019-11-06 Andre Wibisono

Kullback--Leibler (KL) divergence is a fundamental measure of the dissimilarity between two probability distributions, but it can become unstable in high-dimensional settings due to its sensitivity to mismatches in distributional support.…

Information Theory · Computer Science 2025-02-03 Yifeng Peng , Dantong Li , Xinyi Li , Zhiding Liang , Yongshan Ding , Ying Wang

Maximizing the Kullback-Leibler divergence (KLD) is a fundamental problem in waveform design for active sensing and hypothesis testing, as it directly relates to the error exponent of detection probability. However, the associated…

Signal Processing · Electrical Eng. & Systems 2026-01-05 Jeongwoo Park , Seongkyu Jung , Kaiming Shen , Jeonghun Park

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions:…

Statistics Theory · Mathematics 2023-02-17 Matthew Zhang , Sinho Chewi , Mufan Bill Li , Krishnakumar Balasubramanian , Murat A. Erdogdu

Self-supervised sequential recommendation significantly improves recommendation performance by maximizing mutual information with well-designed data augmentations. However, the mutual information estimation is based on the calculation of…

Machine Learning · Computer Science 2023-06-21 Ziwei Fan , Zhiwei Liu , Hao Peng , Philip S Yu

In this paper, we study the numerical discretization of stochastic differential equations with locally Lipschitz, super-linearly growing drift, and the resulting implications for sampling from non-log-concave distributions satisfying a…

Probability · Mathematics 2026-05-26 Iosif Lytras , Angelos Ntousis

We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint…

Machine Learning · Computer Science 2011-09-22 Sarah Filippi , Olivier Cappé , Aurélien Garivier