English
Related papers

Related papers: Training Neural Samplers with Reverse Diffusive KL…

200 papers

Learning word representations has garnered greater attention in the recent past due to its diverse text applications. Word embeddings encapsulate the syntactic and semantic regularities of sentences. Modelling word embedding as multi-sense…

Computation and Language · Computer Science 2019-11-15 P. Jayashree , Ballijepalli Shreya , P. K. Srijith

Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL) loss when using the…

Machine Learning · Computer Science 2025-11-12 Sebastian Sanokowski , Lukas Gruber , Christoph Bartmann , Sepp Hochreiter , Sebastian Lehner

We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regression function using the noise-outsourcing lemma. The proposed…

Statistics Theory · Mathematics 2021-10-22 Xingyu Zhou , Yuling Jiao , Jin Liu , Jian Huang

We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the…

Machine Learning · Computer Science 2026-02-05 Julius Berner , Lorenz Richter , Marcin Sendera , Jarrid Rector-Brooks , Nikolay Malkin

Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation…

Computation and Language · Computer Science 2018-11-14 Zhirui Zhang , Shuangzhi Wu , Shujie Liu , Mu Li , Ming Zhou , Tong Xu

Kullback-Leibler (KL) divergence is a fundamental concept in information theory that quantifies the discrepancy between two probability distributions. In the context of Variational Autoencoders (VAEs), it serves as a central regularization…

Machine Learning · Computer Science 2026-04-14 Andrés Muñoz , Rodrigo Ramele

We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed variable is drawn conditionally on the terminal point of the…

Probability · Mathematics 2019-06-03 Belinda Tzen , Maxim Raginsky

We present an efficient classical algorithm for training deep Boltzmann machines (DBMs) that uses rejection sampling in concert with variational approximations to estimate the gradients of the training objective function. Our algorithm is…

Machine Learning · Computer Science 2015-07-10 Nathan Wiebe , Ashish Kapoor , Christopher Granade , Krysta M Svore

Empirical risk minimization, a cornerstone in machine learning, is often hindered by the Optimizer's Curse stemming from discrepancies between the empirical and true data-generating distributions.To address this challenge, the robust…

Machine Learning · Computer Science 2024-08-20 Haojie Yan , Minglong Zhou , Jiayi Guo

Previously, non-autoregressive models were widely perceived as being superior in generation efficiency but inferior in generation quality due to the difficulties of modeling multiple target modalities. To enhance the multi-modality modeling…

Computation and Language · Computer Science 2023-11-30 Lihua Qian , Mingxuan Wang , Yang Liu , Hao Zhou

This paper investigates the accuracy of generative models and the impact of knowledge transfer on their generation precision. Specifically, we examine a generative model for a target task, fine-tuned using a pre-trained model from a source…

Machine Learning · Statistics 2025-06-03 Xinyu Tian , Xiaotong Shen

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

Efficient sampling of unnormalized probability densities such as the Boltzmann distribution of molecular systems is a longstanding challenge. Next to conventional approaches like molecular dynamics or Markov chain Monte Carlo, variational…

Machine Learning · Computer Science 2025-06-18 Henrik Schopmans , Pascal Friederich

The controllable generation of diffusion models aims to steer the model to generate samples that optimize some given objective functions. It is desirable for a variety of applications including image generation, molecule generation, and…

Machine Learning · Computer Science 2025-05-29 Owen Oertell , Shikun Sun , Yiding Chen , Jin Peng Zhou , Zhiyong Wang , Wen Sun

Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address…

Machine Learning · Statistics 2025-04-29 Steve Hanneke , Samory Kpotufe

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Machine Learning · Statistics 2016-11-29 Dilin Wang , Qiang Liu

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly…

Machine Learning · Computer Science 2026-03-02 Alexander Samarin , Sergei Krutikov , Anton Shevtsov , Sergei Skvortsov , Filipp Fisin , Alexander Golubev

Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions whose support have a complex topological structure, such as…

Machine Learning · Statistics 2022-02-25 Vincent Stimper , Bernhard Schölkopf , José Miguel Hernández-Lobato

Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs). Existing KD methods investigate various divergence measures including the Kullback-Leibler (KL), reverse Kullback-Leibler (RKL), and…

Machine Learning · Computer Science 2024-03-03 Xiao Cui , Yulei Qin , Yuting Gao , Enwei Zhang , Zihan Xu , Tong Wu , Ke Li , Xing Sun , Wengang Zhou , Houqiang Li

In Deep Learning, a well-known approach for training a Deep Neural Network starts by training a generative Deep Belief Network model, typically using Contrastive Divergence (CD), then fine-tuning the weights using backpropagation or other…

Quantum Physics · Physics 2015-10-22 Steven H. Adachi , Maxwell P. Henderson