English
Related papers

Related papers: Channel Simulation and Distributed Compression wit…

200 papers

One-shot channel simulation is a fundamental data compression problem concerned with encoding a single sample from a target distribution $Q$ using a coding distribution $P$ using as few bits as possible on average. Algorithms that solve…

Information Theory · Computer Science 2024-04-01 Gergely Flamich

One-shot channel simulation has recently emerged as a promising alternative to quantization and entropy coding in machine-learning-based lossy data compression schemes. However, while there are several potential applications of channel…

Information Theory · Computer Science 2024-05-07 Daniel Goc , Gergely Flamich

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Computation and Language · Computer Science 2025-12-18 Chendong Sun , Ali Mao , Lei Xu , mingmin Chen

We introduce Ensemble Rejection Sampling, a scheme for exact simulation from the posterior distribution of the latent states of a class of non-linear non-Gaussian state-space models. Ensemble Rejection Sampling relies on a proposal for the…

Computation · Statistics 2020-01-28 George Deligiannidis , Arnaud Doucet , Sylvain Rubenthaler

A non-uniform channel input distribution is key for achieving the capacity of arbitrary channels. However, message bits are generally assumed to follow a uniform distribution which must first be transformed to a non-uniform distribution by…

Information Theory · Computer Science 2025-12-19 Frederik Ritter , Andrej Rode , Laurent Schmalen

We present herein a scheme by which to accurately evaluate the error exponents of a lossy data compression problem, which characterize average probabilities over a code ensemble of compression failure and success above or below a critical…

Statistical Mechanics · Physics 2007-05-23 Tadaaki Hosaka , Yoshiyuki Kabashima

Distributed high dimensional mean estimation is a common aggregation routine used often in distributed optimization methods. Most of these applications call for a communication-constrained setting where vectors, whose mean is to be…

Machine Learning · Statistics 2026-01-28 Harsh Vardhan , Arya Mazumdar

This thesis presents Regenerative Rejection Sampling (RRS), a novel approximate sampling algorithm inspired by classical Rejection Sampling and Markov Chain Monte Carlo methods. The method constructs a continuous-time regenerative process…

Computation · Statistics 2026-04-01 Tommaso Bozzi

We study a relaxation of the problem of coupling probability distributions -- a list of samples is generated from one distribution and an accept is declared if any one of these samples is identical to the sample generated from the other…

Machine Learning · Computer Science 2026-01-13 Joseph Rowan , Buu Phan , Ashish Khisti

Rejection sampling is a technique for sampling from difficult distributions. However, its use is limited due to a high rejection rate. Common adaptive rejection sampling methods either work only for very specific distributions or without…

Machine Learning · Statistics 2026-04-27 Akram Erraqabi , Michal Valko , Alexandra Carpentier , Odalric-Ambrym Maillard

We propose two extensions to existing importance sampling based methods for lossy compression. First, we introduce an importance sampling based compression scheme that is a variant of ordered random coding (Theis and Ahmed, 2022) and is…

Information Theory · Computer Science 2024-03-11 Buu Phan , Ashish Khisti , Christos Louizos

Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained generation fall along a spectrum: greedy constrained decoding…

Artificial Intelligence · Computer Science 2025-10-03 Paweł Parys , Sairam Vaidya , Taylor Berg-Kirkpatrick , Loris D'Antoni

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch…

Machine Learning · Computer Science 2017-05-08 Nicolas Keriven , Anthony Bourrier , Rémi Gribonval , Patrick Pérez

We consider channel simulation protocols between two communicating parties, Alice and Bob. First, Alice receives a target distribution $Q$, unknown to Bob. Then, she employs a shared coding distribution $P$ to send the minimum amount of…

Information Theory · Computer Science 2024-05-16 Gergely Flamich , Lucas Theis

We propose a rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution. We show that under quite strict assumptions, this will allow us to recover the data distribution…

Machine Learning · Statistics 2019-02-27 Samaneh Azadi , Catherine Olsson , Trevor Darrell , Ian Goodfellow , Augustus Odena

In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this using as few samples as possible. In the…

Machine Learning · Statistics 2015-02-26 Roy Frostig , Rong Ge , Sham M. Kakade , Aaron Sidford

Doubly selective (DS) channel estimation in largescale multiple-input multiple-output (MIMO) systems is a challenging problem due to the requirement of unaffordable pilot overheads and prohibitive complexity. In this paper, we propose a…

Information Theory · Computer Science 2015-11-10 Bo Gong , Qibo Qin , Xiang Ren , Lin Gui , Hanwen Luo , Wen Chen

Relative entropy coding (REC) algorithms encode a sample from a target distribution $Q$ using a proposal distribution $P$ using as few bits as possible. Unlike entropy coding, REC does not assume discrete distributions or require…

Information Theory · Computer Science 2023-09-28 Gergely Flamich , Stratis Markou , Jose Miguel Hernandez Lobato

Ensemble methods are among the state-of-the-art predictive modeling approaches. Applied to modern big data, these methods often require a large number of sub-learners, where the complexity of each learner typically grows with the size of…

Machine Learning · Computer Science 2018-10-29 Amichai Painsky , Saharon Rosset

We consider a monitoring application where sensors periodically report data to a common receiver in a time division multiplex fashion. The sensors are constrained by the limited and unpredictable energy availability provided by Energy…

Information Theory · Computer Science 2017-06-29 Chiara Pielli , Cedomir Stefanovic , Petar Popovski , Michele Zorzi
‹ Prev 1 2 3 10 Next ›