English
Related papers

Related papers: Large Alphabet Compression and Predictive Distribu…

200 papers

A compression function is a map that slims down an observational set into a subset of reduced size, while preserving its informational content. In multiple applications, the condition that one new observation makes the compressed set change…

Machine Learning · Computer Science 2024-01-09 Marco C. Campi , Simone Garatti

The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limited by a foundational issue: they are trained on discrete…

The Poisson multinomial distribution (PMD) describes the distribution of the sum of $n$ independent but non-identically distributed random vectors, in which each random vector is of length $m$ with 0/1 valued elements and only one of its…

Computation · Statistics 2022-01-13 Zhengzhi Lin , Yueyao Wang , Yili Hong

I propose a variational approach to maximum pseudolikelihood inference of the Ising model. The variational algorithm is more computationally efficient, and does a better job predicting out-of-sample correlations than $L_2$ regularized…

Statistical Mechanics · Physics 2014-09-26 Charles K. Fisher

Compound Poisson distributions have been employed by many authors to fit experimental data, typically via the method of moments or maximum likelihood estimation. We propose a new technique and apply it to several sets of published data. It…

Methodology · Statistics 2025-04-01 S. R. Mane

Most work on supervised learning research has focused on marginal predictions. In decision problems, joint predictive distributions are essential for good performance. Previous work has developed methods for assessing low-order predictive…

Machine Learning · Statistics 2022-03-01 Ian Osband , Zheng Wen , Seyed Mohammad Asghari , Vikranth Dwaracherla , Xiuyuan Lu , Benjamin Van Roy

The goal of subsampling is to select an informative subset of all observations, when using the full data for statistical analysis is not viable. We construct locally $ D $-optimal subsampling designs under a Poisson regression model with a…

Statistics Theory · Mathematics 2024-03-28 Torsten Reuter , Rainer Schwabe

We give an algorithm that learns a representation of data through compression. The algorithm 1) predicts bits sequentially from those previously seen and 2) has a structure and a number of computations similar to an autoencoder. The…

Computer Vision and Pattern Recognition · Computer Science 2011-08-05 Karol Gregor , Yann LeCun

We present a new, analytic, Poisson likelihood derived, technique to account for the statistical uncertainties inherent in simulation samples of limited size. This method has better coverage properties than other techniques, is valid for…

Data Analysis, Statistics and Probability · Physics 2019-07-26 Carlos A. Argüelles , Austin Schneider , Tianlu Yuan

A composite likelihood is an inference function derived by multiplying a set of likelihood components. This approach provides a flexible framework for drawing inference when the likelihood function of a statistical model is computationally…

Methodology · Statistics 2024-12-10 Giuseppe Alfonzetti , Ruggero Bellio , Yunxiao Chen , Irini Moustaki

A change of the prevalent supervised learning techniques is foreseeable in the near future: from the complex, computational expensive algorithms to more flexible and elementary training ones. The strong revitalization of randomized…

Machine Learning · Computer Science 2022-09-02 Antonello Rosato , Massimo Panella , Evgeny Osipov , Denis Kleyko

Nonparametric regression for massive numbers of samples (n) and features (p) is an increasingly important problem. In big n settings, a common strategy is to partition the feature space, and then separately apply simple models to each…

Machine Learning · Statistics 2014-06-10 Rajarshi Guhaniyogi , David B. Dunson

A number of engineering and scientific problems require representing and manipulating probability distributions over large alphabets, which we may think of as long vectors of reals summing to $1$. In some cases it is required to represent…

Information Theory · Computer Science 2023-10-27 Aviv Adler , Jennifer Tang , Yury Polyanskiy

We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding…

Computation and Language · Computer Science 2023-12-07 Arthur Hemmer , Mickaël Coustaty , Nicola Bartolo , Jérôme Brachat , Jean-Marc Ogier

Universal source coding at short blocklengths is considered for an exponential family of distributions. The \emph{Type Size} code has previously been shown to be optimal up to the third-order rate for universal compression of all memoryless…

Information Theory · Computer Science 2016-12-21 Nematollah Iri , Oliver Kosut

Sequential probability assignment and universal compression go hand in hand. We propose sequential probability assignment for non-binary (and large alphabet) sequences with empirical distributions whose parameters are known to be bounded…

Information Theory · Computer Science 2021-02-09 Michael Drmota , Gil Shamir , Wojciech Szpankowski

As large language models (LLMs) continue to be deployed and utilized across domains, the volume of LLM-generated data is growing rapidly. This trend highlights the increasing importance of effective and lossless compression for such data in…

Machine Learning · Computer Science 2025-05-13 Yu Mao , Holger Pirk , Chun Jason Xue

In this paper, we propose improved estimation method for logistic regression based on subsamples taken according the optimal subsampling probabilities developed in Wang et al. 2018 Both asymptotic results and numerical results show that the…

Methodology · Statistics 2021-06-24 HaiYing Wang

Sparse representation-based classifiers have shown outstanding accuracy and robustness in image classification tasks even with the presence of intense noise and occlusion. However, it has been discovered that the performance degrades…

Computer Vision and Pattern Recognition · Computer Science 2015-12-22 Xiaoxia Sun , Nasser M. Nasrabadi , Trac D. Tran

Cross-classified data frequently arise in scientific fields such as education, healthcare, and social sciences. A common modeling strategy is to introduce crossed random effects within a regression framework. However, this approach often…

Methodology · Statistics 2025-07-22 Shota Takeishi , Shonosuke Sugasawa
‹ Prev 1 3 4 5 6 7 10 Next ›