English
Related papers

Related papers: Large Alphabet Compression and Predictive Distribu…

200 papers

The Poisson distribution arises naturally when dealing with data involving counts, and it has found many applications in inverse problems and imaging. In this work, we develop an approximate Bayesian inference technique based on expectation…

Numerical Analysis · Mathematics 2019-09-04 Chen Zhang , Simon Arridge , Bangti Jin

Given a collection of strings, each with an associated probability of occurrence, the guesswork of each of them is their position in a list ordered from most likely to least likely, breaking ties arbitrarily. Guesswork is central to several…

Information Theory · Computer Science 2019-08-12 Ahmad Beirami , Robert Calderbank , Mark Christiansen , Ken Duffy , Muriel Médard

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

The problem of guessing a random string is revisited. A close relation between guessing and compression is first established. Then it is shown that if the sequence of distributions of the information spectrum satisfies the large deviation…

Information Theory · Computer Science 2010-08-12 Manjesh Kumar Hanawal , Rajesh Sundaresan

We present a one-shot method for compressing large labeled graphs called Random Edge Coding. When paired with a parameter-free model based on P\'olya's Urn, the worst-case computational and memory complexities scale quasi-linearly and…

Machine Learning · Computer Science 2023-05-18 Daniel Severo , James Townsend , Ashish Khisti , Alireza Makhzani

The efficient communication of noisy data has applications in several areas of machine learning, such as neural compression or differential privacy, and is also known as reverse channel coding or the channel simulation problem. Here we…

Information Theory · Computer Science 2022-05-26 Lucas Theis , Noureldin Yosri

We consider a variant of the channel simulation problem with a single input and multiple outputs, where Alice observes a probability distribution $P$ from a set of prescribed probability distributions $\mathbb{\mathcal{P}}$, and sends a…

Information Theory · Computer Science 2021-09-07 Chak Fung Choi , Cheuk Ting Li

We consider the following communication task in the multi-party setting, which involves a joint random variable $XYZMN$ with the property that $M$ is independent of $YZN$ conditioned on $X$ and $N$ is independent of $XZM$ conditioned on…

Information Theory · Computer Science 2020-03-24 Anurag Anshu , Penghui Yao

Large alphabet source coding is a basic and well-studied problem in data compression. It has many applications such as compression of natural language text, speech and images. The classic perception of most commonly used methods is that a…

Information Theory · Computer Science 2016-07-26 Amichai Painsky , Saharon Rosset , Meir Feder

The negative binomial distribution has been widely used as a more flexible model than the Poisson distribution for count data. However, when the true data-generating process is Poisson, it is often challenging to distinguish it from a…

Statistics Theory · Mathematics 2026-04-07 Yingying Yang , Niloufar Dousti Mousavi , Zhou Yu , Jie Yang

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

In this paper we exploit concepts of information theory to address the fundamental problem of identifying and defining the most suitable tools to extract, in a automatic and agnostic way, information from a generic string of characters. We…

Statistical Mechanics · Physics 2009-11-10 Andrea Baronchelli , Emanuele Caglioti , Vittorio Loreto

Packing and shuffling tokens is a common practice in training auto-regressive language models (LMs) to prevent overfitting and improve efficiency. Typically documents are concatenated to chunks of maximum sequence length (MSL) and then…

Computation and Language · Computer Science 2024-08-20 Yanbing Chen , Ruilin Wang , Zihao Yang , Lavender Yao Jiang , Eric Karl Oermann

In this paper, we have developed a new class of sampling schemes for estimating parameters of binomial and Poisson distributions. Without any information of the unknown parameters, our sampling schemes rigorously guarantee prescribed levels…

Statistics Theory · Mathematics 2009-10-11 Xinjia Chen

Large-alphabet strings are common in scenarios such as information retrieval and natural-language processing. The efficient storage and processing of such strings usually introduces several challenges that are not witnessed in…

Data Structures and Algorithms · Computer Science 2024-05-03 Diego Arroyuelo , Gabriel Carmona , Héctor Larrañaga , Francisco Riveros , Carlos Eugenio Rojas-Morales , Erick Sepúlveda

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Computation and Language · Computer Science 2024-02-16 Wenxiao Wang , Wei Chen , Yicong Luo , Yongliu Long , Zhengkai Lin , Liye Zhang , Binbin Lin , Deng Cai , Xiaofei He

We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a Beta Process. It also…

Computer Vision and Pattern Recognition · Computer Science 2015-03-30 Naveed Akhtar , Faisal Shafait , Ajmal Mian

Counting experiments often rely on Monte Carlo simulations for predictions of Poisson expectations. The accompanying uncertainty from the finite Monte Carlo sample size can be incorporated into parameter estimation by modifying the Poisson…

Instrumentation and Methods for Astrophysics · Physics 2020-04-22 Thorsten Glüsenkamp

We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a…

Machine Learning · Statistics 2025-12-04 Jean Pachebat , Giovanni Conforti , Alain Durmus , Yazid Janati

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post