中文
相关论文

相关论文: Martin-L\"of reducibility and cost functions

200 篇论文

Open sets are central to mathematics, especially analysis and topology, in ways few notions are. In most, if not all, computational approaches to mathematics, open sets are only studied indirectly via their 'codes' or 'representations'. In…

逻辑 · 数学 2024-08-15 Dag Normann , Sam Sanders

We introduce a notion of computable randomness for infinite sequences that generalises the classical version in two important ways. First, our definition of computable randomness is associated with imprecise probability models, in the sense…

概率论 · 数学 2020-09-23 Floris Persiau , Jasper De Bock , Gert de Cooman

Reproducibility is a cornerstone of scientific validation and of the authority it confers on its results. Reproducibility in machine learning evaluations leads to greater trust, confidence, and value. However, the ground truth responses…

机器学习 · 计算机科学 2025-12-12 Deepak Pandita , Flip Korn , Chris Welty , Christopher M. Homan

This paper introduces a framework for modeling the cost of information acquisition based on the principle of cost-minimization. We study the reduced-form \emph{indirect cost} of information generated by the sequential minimization of a…

理论经济学 · 经济学 2025-11-10 Alexander W. Bloedel , Weijie Zhong

When in a full exponential family the maximum likelihood estimate (MLE) does not exist, the MLE may exist in the Barndorff-Nielsen completion of the family. We propose a practical algorithm for finding the MLE in the completion based on…

统计理论 · 数学 2009-01-06 Charles J. Geyer

A model of computation for which reasonable yet still incomplete lower bounds are known is the read-once branching program. Here variants of complexity measures successful in the study of read-once branching programs are defined and…

计算复杂性 · 计算机科学 2023-05-22 Yaqiao Li , Pierre McKenzie

Nolan and Temple Lang argue that "the ability to express statistical computations is an essential skill." A key related capacity is the ability to conduct and present data analysis in a way that another person can understand and replicate.…

其他统计学 · 统计学 2023-08-29 Ben Baumer , Mine Cetinkaya-Rundel , Andrew Bray , Linda Loi , Nicholas J. Horton

In this survey we discuss work of Levin and V'yugin on collections of sequences that are non-negligible in the sense that they can be computed by a probabilistic algorithm with positive probability. More precisely, Levin and V'yugin…

逻辑 · 数学 2021-05-19 Rupert Hölzl , Christopher P. Porter

The low-rank approximation properties of Randomly Pivoted LU (RPLU), a variant of Gaussian elimination where pivots are sampled proportional to the squared entries of the Schur complement, are analyzed. It is shown that the RPLU iterates…

数值分析 · 数学 2026-02-02 Marc Aurèle Gilles , Heather Wilber

The notion of Schnorr randomness refers to computable reals or computable functions. We propose a version of Schnorr randomness for subcomputable classes and characterize it in different ways: by Martin L\"of tests, martingales or measure…

计算机科学中的逻辑 · 计算机科学 2019-03-14 Claude Sureson

The program Reverse Mathematics (RM for short) seeks to identify the axioms necessary to prove theorems of ordinary mathematics, usually working in the language of second-order arithmetic $L_{2}$. A major theme in RM is therefore the study…

逻辑 · 数学 2021-08-17 Sam Sanders

We consider the numerical approximation of $\mathbb{P}[G\in \Omega]$ where the $d$-dimensional random variable $G$ cannot be sampled directly, but there is a hierarchy of increasingly accurate approximations $\{G_\ell\}_{\ell\in\mathbb{N}}$…

计算金融 · 定量金融 2021-07-21 Abdul-Lateef Haji-Ali , Jonathan Spence , Aretha Teckentrup

Langevin Monte Carlo (LMC) is a popular Bayesian sampling method. For the log-concave distribution function, the method converges exponentially fast, up to a controllable discretization error. However, the method requires the evaluation of…

机器学习 · 统计学 2025-03-07 Zhiyan Ding , Qin Li

In Chapter 3 of his Notes on constructive mathematics, Martin-L{\"o}f describes recursively constructed ordinals. He gives a constructively acceptable version of Kleene's computable ordinals. In fact, the Turing definition of computable…

逻辑 · 数学 2024-12-11 Thierry Coquand , Henri Lombardi , Stefan Neuwirth

The problem of optimising functions with intractable gradients frequently arise in machine learning and statistics, ranging from maximum marginal likelihood estimation procedures to fine-tuning of generative models. Stochastic approximation…

机器学习 · 统计学 2026-01-30 James Cuin , Davide Carbone , Yanbo Tang , O. Deniz Akyildiz

We present a numerical iterative optimization algorithm for the minimization of a cost function consisting of a linear combination of three convex terms, one of which is differentiable, a second one is prox-simple and the third one is the…

最优化与控制 · 数学 2024-10-04 Ignace Loris , Simone Rebegoldi

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

Solovay proved that there exists a computable upper bound f of the prefix-free Kolmogorov complexity function K such that f (x) = K(x) for infinitely many x. In this paper, we consider the class of computable functions f such that K(x) <= f…

计算复杂性 · 计算机科学 2009-02-10 Laurent Bienvenu , Rod Downey

The Jordan decomposition theorem states that every function $f \colon [0,1] \to \mathbb{R}$ of bounded variation can be written as the difference of two non-decreasing functions. Combining this fact with a result of Lebesgue, every function…

逻辑 · 数学 2021-01-11 André Nies , Marcus A. Triplett , Keita Yokoyama

This work proposes a novel general-purpose estimator for supervised machine learning (ML) based on tensor trains (TT). The estimator uses TTs to parametrize discretized functions, which are then optimized using Riemannian gradient descent…

机器学习 · 计算机科学 2022-03-10 Bart Vandereycken , Rik Voorhaar