中文
相关论文

相关论文: Prediction of Large Alphabet Processes and Its App…

200 篇论文

The problem is sequence prediction in the following setting. A sequence $x_1,...,x_n,...$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\mu$. After observing each outcome, it is required…

人工智能 · 计算机科学 2012-03-20 Daniil Ryabko

The scheme of the sliding window is known in Information Theory, Computer Science, the problem of predicting and in stastistics. Let a source with unknown statistics generate some word $... x_{-1}x_{0}x_{1}x_{2}...$ in some alphabet $A$.…

信息论 · 计算机科学 2008-09-30 Boris Ryabko

Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only…

机器学习 · 计算机科学 2013-07-02 Tor Lattimore , Marcus Hutter , Peter Sunehag

The problem is sequence prediction in the following setting. A sequence x1,..., xn,... of discrete-valued observations is generated according to some unknown probabilistic law (measure) mu. After observing each outcome, it is required to…

机器学习 · 计算机科学 2015-10-19 Daniil Ryabko

Given a prefix (context), open-ended generation aims to decode texts that are coherent, which do not abruptly drift from previous topics, and informative, which do not suffer from undesired repetitions. In this paper, we propose Look-back,…

计算与语言 · 计算机科学 2023-10-24 Nan Xu , Chunting Zhou , Asli Celikyilmaz , Xuezhe Ma

Universal compression of patterns of sequences generated by independently identically distributed (i.i.d.) sources with unknown, possibly large, alphabets is investigated. A pattern is a sequence of indices that contains all consecutive…

信息论 · 计算机科学 2016-11-17 Gil I. Shamir

We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal bounds on the expected risk are known, high-probability…

统计理论 · 数学 2026-02-27 Jaouad Mourtada

We address the problem of constructing a fast lossless code in the case when the source alphabet is large. The main idea of the new scheme may be described as follows. We group letters with small probabilities in subsets (acting as super…

信息论 · 计算机科学 2007-07-13 Boris Ryabko , Jaakko Astola , Karen Egiazarian

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…

信息论 · 计算机科学 2016-07-26 Amichai Painsky , Saharon Rosset , Meir Feder

The forward prediction problem for a binary time series $\{X_n\}_{n=0}^{\infty}$ is to estimate the probability that $X_{n+1}=1$ based on the observations $X_i$, $0\le i\le n$ without prior knowledge of the distribution of the process…

概率论 · 数学 2008-06-19 Gusztav Morvai

Adaptive coding faces the following problem: given a collection of source classes such that each class in the collection has non-trivial minimax redundancy rate, can we design a single code which is asymptotically minimax over each class in…

信息论 · 计算机科学 2016-09-02 Anna Ben-Hamou , Stephane Boucheron , Elisabeth Gassiat

We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM…

计算与语言 · 计算机科学 2023-11-01 Qinyuan Ye , Harvey Yiyun Fu , Xiang Ren , Robin Jia

The Kullback-Leibler (KL) divergence is a fundamental equation of information theory that quantifies the proximity of two probability distributions. Although difficult to understand by examining the equation, an intuition and understanding…

信息论 · 计算机科学 2014-04-09 Jonathon Shlens

Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are…

计算与语言 · 计算机科学 2019-05-07 Weijia Xu , Xing Niu , Marine Carpuat

Article discusses the application of Kullback-Leibler divergence to the recognition of speech signals and suggests three algorithms implementing this divergence criterion: correlation algorithm, spectral algorithm and filter algorithm.…

人工智能 · 计算机科学 2007-05-23 Igor Bocharov , Pavel Lukin

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations. However,…

计算与语言 · 计算机科学 2026-04-16 Aleksandr Rubashevskii , Dzianis Piatrashyn , Preslav Nakov , Maxim Panov

We consider the problem of reducing a first-order Markov chain on a large alphabet to a higher-order Markov chain on a small alphabet. We present information-theoretic cost functions that are related to predictability and lumpability, show…

信息论 · 计算机科学 2017-06-13 Bernhard C. Geiger , Yuchen Wu

For the discrete memoryless sources with a countably infinite alphabet, we prove that for any positive integer $k$, there exists a corresponding probability interval such that if the largest symbol probability $p_{1}$ falls in this…

信息论 · 计算机科学 2026-04-21 Hongyang Liu , Wei Yan

Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…

软件工程 · 计算机科学 2026-01-01 David Gros , Prem Devanbu

F.Giroire has recently proposed an algorithm which returns the approximate number of distincts elements in a large sequence of words, under strong constraints coming from the analysis of large data bases. His estimation is based on…

统计理论 · 数学 2011-04-25 Philippe Chassaing , Lucas Gerin
‹ 上一页 1 2 3 10 下一页 ›