English
Related papers

Related papers: A Block Metropolis-Hastings Sampler for Controllab…

200 papers

Markov Chain Monte Carlo methods are widely used in signal processing and communications for statistical inference and stochastic optimization. In this work, we introduce an efficient adaptive Metropolis-Hastings algorithm to draw samples…

Computation · Statistics 2016-03-17 David Luengo , Luca Martino

Large Language Models (LLMs) have revolutionised the field of Natural Language Processing (NLP) and have achieved state-of-the-art performance in practically every task in this field. However, the prevalent approach used in text generation,…

Computation and Language · Computer Science 2024-08-12 Nicolo Micheletti , Samuel Belkadi , Lifeng Han , Goran Nenadic

In recent years, there has been a growing interest in the development of language models capable of generating text with controllable attributes. While several approaches have been proposed, many of these methods require condition-specific…

Computation and Language · Computer Science 2023-02-22 Shangda Wu , Maosong Sun

In this paper we introduce a new sampling algorithm which has the potential to be adopted as a universal replacement to the Metropolis--Hastings algorithm. It is related to the slice sampler, and motivated by an algorithm which is…

Computation · Statistics 2020-10-19 Yanxin Li , Stephen G. Walker

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…

Computation and Language · Computer Science 2021-04-15 Bowen Tan , Zichao Yang , Maruan AI-Shedivat , Eric P. Xing , Zhiting Hu

Global fits of physics models require efficient methods for exploring high-dimensional and/or multimodal posterior functions. We introduce a novel method for accelerating Markov Chain Monte Carlo (MCMC) sampling by pairing a…

High Energy Physics - Phenomenology · Physics 2023-09-06 N. T. Hunt-Smith , W. Melnitchouk , F. Ringer , N. Sato , A. W Thomas , M. J. White

Energy-Based Models (EBMs) allow for extremely flexible specifications of probability distributions. However, they do not provide a mechanism for obtaining exact samples from these distributions. Monte Carlo techniques can aid us in…

Machine Learning · Computer Science 2021-12-13 Bryan Eikema , Germán Kruszewski , Hady Elsahar , Marc Dymetman

A Kernel Adaptive Metropolis-Hastings algorithm is introduced, for the purpose of sampling from a target distribution with strongly nonlinear support. The algorithm embeds the trajectory of the Markov chain into a reproducing kernel Hilbert…

Machine Learning · Statistics 2014-06-16 Dino Sejdinovic , Heiko Strathmann , Maria Lomeli Garcia , Christophe Andrieu , Arthur Gretton

Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…

Computation and Language · Computer Science 2022-05-05 Antoine Chaffin , Vincent Claveau , Ewa Kijak

We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data. Previous work on reducing the cost of Metropolis-Hastings tests yield variable data consumed per sample, with only constant…

Machine Learning · Computer Science 2017-07-11 Daniel Seita , Xinlei Pan , Haoyu Chen , John Canny

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…

Machine Learning · Computer Science 2023-04-05 Jaewoong Lee , Sangwon Jang , Jaehyeong Jo , Jaehong Yoon , Yunji Kim , Jin-Hwa Kim , Jung-Woo Ha , Sung Ju Hwang

Many recent reasoning gains in large language models can be explained as distribution sharpening: biasing generation toward high-likelihood trajectories already supported by the pretrained model, rather than modifying its weights. A natural…

Machine Learning · Statistics 2026-03-24 Seyedarmin Azizi , Erfan Baghaei Potraghloo , Minoo Ahmadi , Souvik Kundu , Massoud Pedram

Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as…

Computation and Language · Computer Science 2020-11-05 Junxian He , Taylor Berg-Kirkpatrick , Graham Neubig

Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall within a specific length range, making length controlled…

Computation and Language · Computer Science 2024-06-18 Renlong Jie , Xiaojun Meng , Lifeng Shang , Xin Jiang , Qun Liu

Monte Carlo (MC) sampling methods are widely applied in Bayesian inference, system simulation and optimization problems. The Markov Chain Monte Carlo (MCMC) algorithms are a well-known class of MC methods which generate a Markov chain with…

Methodology · Statistics 2024-06-21 Luca Martino , Victor Elvira

Can we make Bayesian posterior MCMC sampling more efficient when faced with very large datasets? We argue that computing the likelihood for N datapoints in the Metropolis-Hastings (MH) test to reach a single binary decision is…

Machine Learning · Computer Science 2014-02-17 Anoop Korattikara , Yutian Chen , Max Welling

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Computation and Language · Computer Science 2025-02-07 Patrick Pynadath , Ruqi Zhang

Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models. We address these…

Computation and Language · Computer Science 2025-06-06 Zeno Belligoli , Emmanouil Stergiadis , Eran Fainman , Ilya Gusev

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

Over the last decades, various "non-linear" MCMC methods have arisen. While appealing for their convergence speed and efficiency, their practical implementation and theoretical study remain challenging. In this paper, we introduce a…

Statistics Theory · Mathematics 2022-08-04 Grégoire Clarté , Antoine Diez , Jean Feydy