English
Related papers

Related papers: Bounds for Algorithmic Mutual Information and a Un…

200 papers

The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this work, we identify a significant subclass of MOMDPs defined by…

Robotics · Computer Science 2022-06-07 Hai Nguyen , Zhihan Yang , Andrea Baisero , Xiao Ma , Robert Platt , Christopher Amato

Given finite-dimensional random vectors $Y$, $X$, and $Z$ that form a Markov chain in that order (i.e., $Y \to X \to Z$), we derive upper bounds on the excess minimum risk using generalized information divergence measures. Here, $Y$ is a…

Information Theory · Computer Science 2025-06-02 Ananya Omanwar , Fady Alajaji , Tamás Linder

Some new results are derived concerning random coding error exponents and expurgated exponents for list decoding with a deterministic list size $L$. Two asymptotic regimes are considered, the fixed list-size regime, where $L$ is fixed…

Information Theory · Computer Science 2016-11-17 Neri Merhav

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive)…

Artificial Intelligence · Computer Science 2017-06-20 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

We observe a length-$n$ sample generated by an unknown,stationary ergodic Markov process (\emph{model}) over a finite alphabet $\mathcal{A}$. Given any string $\bf{w}$ of symbols from $\mathcal{A}$ we want estimates of the conditional…

Information Theory · Computer Science 2014-06-11 Meysam Asadi , Ramezan Paravi Torghabeh , Narayana P. Santhanam

We consider the problem of estimating the number of distinct elements in a large data set (or, equivalently, the support size of the distribution induced by the data set) from a random sample of its elements. The problem occurs in many…

Machine Learning · Computer Science 2021-06-17 Talya Eden , Piotr Indyk , Shyam Narayanan , Ronitt Rubinfeld , Sandeep Silwal , Tal Wagner

We derive the property of strong superadditivity of mutual information arising from the Markov property of the vacuum state in a conformal field theory and strong subadditivity of entanglement entropy. We show this inequality encodes…

High Energy Physics - Theory · Physics 2021-09-29 Horacio Casini , Eduardo Testé , Gonzalo Torroba

This paper considers distributed average consensus using finite-bit bounded quantizer with possibly unbounded data. Under the framework of the alternating direction method of multipliers (ADMM), we develop distributed averaging algorithms…

Optimization and Control · Mathematics 2017-08-22 Shengyu Zhu , Biao Chen

With the ascent of large language models (LLM), natural language processing has witnessed enhancements, such as LLM-based data augmentation. Nonetheless, prior research harbors two primary concerns: firstly, a lack of contemplation…

Computation and Language · Computer Science 2024-07-02 Zhenhua Wang , Guang Xu , Ming Ren

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were previously available…

Machine Learning · Computer Science 2020-06-25 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat…

Computation and Language · Computer Science 2024-09-18 Jianing Wang , Yang Zhou , Xiaocheng Zhang , Mengjiao Bao , Peng Yan

Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…

Machine Learning · Computer Science 2026-05-14 Yifan Zhang

To characterize the Kullback-Leibler divergence and Fisher information in general parametrized hidden Markov models, in this paper, we first show that the log likelihood and its derivatives can be represented as an additive functional of a…

Statistics Theory · Mathematics 2023-03-15 Cheng-Der Fuh , Chu-Lan Michael Kao , Tianxiao Pang

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where continual training on…

Machine Learning · Computer Science 2025-10-01 Ming Yang , Xiaofan Li , Zhiyuan Ma , Dengliang Shi , Jintao Du , Yu Cheng , Weiguo Zheng

We develop a novel framework for costly information acquisition in which a decision-maker learns about an unobserved state by choosing a signal distribution, with the cost of information determined by the distribution of noise in the…

Theoretical Economics · Economics 2025-03-27 Peter Achim , Kemal Ozbek

We present a new notion $R_\ell$ of higher-order common information, which quantifies the information that $\ell\geq 2$ arbitrarily distributed random variables have in common. We provide analytical lower bounds on $R_3$ and $R_4$ for…

Information Theory · Computer Science 2024-06-05 Jan Østergaard

This paper presents some results on the maximum likelihood (ML) estimation from incomplete data. Finite sample properties of conditional observed information matrices are established. They possess positive definiteness and the same Loewner…

Methodology · Statistics 2022-07-26 Budhi Arta Surya

Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as momentum, SPIDER, STORM, and PAGE have been highly…

Machine Learning · Computer Science 2026-05-18 Zhankun Luo , Antesh Upadhyay , M. Berk Sahin , Sang Bin Moon , Anuran Makur , Abolfazl Hashemi

How should one combine noisy information from diverse sources to make an inference about an objective ground truth? This frequently recurring, normative question lies at the core of statistics, machine learning, policy-making, and everyday…

Multiagent Systems · Computer Science 2020-01-29 Silviu Pitis , Michael R. Zhang

We study the generalization error of stochastic learning algorithms from an information-theoretic perspective, with a particular emphasis on deriving sharper bounds for differentially private algorithms. It is well known that the…

Information Theory · Computer Science 2026-04-20 Yanxiao Liu , Chun Hei Michael Shiu , Lele Wang , Deniz Gündüz
‹ Prev 1 8 9 10 Next ›