Suchergebnisse - Approximate sample error minimization algorithm

Learning from non-irreducible Markov chains von Sandrić, Nikola, Šebek, Stjepan

“… Most of the existing literature on supervised machine learning problems focuses on the case when the training data set is drawn from an i.i.d. sample …”
Volltext

Optimal Subsampling for Large Sample Logistic Regression von Wang, HaiYing, Zhu, Rong, Ma, Ping

“… In this article, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression …”
Volltext

Phase Transition of Total Variation Based on Approximate Message Passing Algorithm von Cheng, Xiang, Lei, Hong

“… In compressed sensing (CS), one seeks to down-sample some high-dimensional signals and recover them accurately by exploiting the sparsity of the signals …”
Volltext

Rademacher learning rates for iterated random functions von Sandrić, Nikola

“… Most supervised learning methods assume training data is drawn from an i.i.d. sample. However, real-world problems often exhibit temporal dependence and strong correlations between marginals of the data-generating process, rendering …”
Volltext

A Canonical Form for Weighted Automata and Applications to Approximate Minimization von Balle, Borja, Panangaden, Prakash, Precup, Doina

“… We study the problem of constructing approximations to a weighted automaton. Weighted finite automata (WFA) are closely related to the theory of rational …”
Volltext

Learning from non-irreducible Markov chains von Sandrić, Nikola, Šebek, Stjepan

“… Mostof the existing literature on supervised machine learning problems focuses on the case when the training data set is drawn from an i.i.d. sample …”
Volltext

A Randomized Algorithm for Nonconvex Minimization With Inexact Evaluations and Complexity Guarantees von Li, Shuyao, Wright, Stephen J.

“… We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian …”
Volltext

Efficient Data Placement and Replication for QoS-Aware Approximate Query Evaluation of Big Data Analytics von Xia, Qiufen, Xu, Zichuan, Liang, Weifa, Yu, Shui, Guo, Song, Zomaya, Albert Y.

“… Instead, sometimes users may only be interested in timely approximate rather than exact query results …”
Volltext

Minimization for conditional simulation: Relationship to optimal transport von Oliver, Dean S.

“… In this paper, we consider the problem of generating independent samples from a conditional distribution when independent samples from the prior distribution are available …”
Volltext

Approximation of frame based missing data recovery von Cai, Jian-Feng, Shen, Zuowei, Ye, Gui-Bo

“… While many such algorithms have been developed recently, there are very few papers available on their error estimations …”
Volltext

A deep neural network-based method for solving obstacle problems von Cheng, Xiaoliang, Shen, Xing, Wang, Xilu, Liang, Kewei

“… The approximate error is bounded by the depth and width of the network, the statistical error is estimated by the number of samples, and the optimization error is reflected in the empirical loss term …”
Volltext

On optimal selection of summary statistics for approximate Bayesian computation von Nunes, Matthew A, Balding, David J

“… We approach it from the point of view of seeking data summaries that minimize the average squared error of the posterior distribution for a parameter of interest under approximate Bayesian computation (ABC …”
Weitere Angaben

Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations von Berner, Julius, Grohs, Philipp, Jentzen, Arnulf

“… The development of new classification and regression algorithms based on empirical risk minimization (ERM …”
Volltext

Near-optimality of greedy set selection in the sampling of graph signals von Chamon, Luiz F. O., Ribeiro, Alejandro

“… Still, sampling set selection remains an open issue. Indeed, although conditions for graph signal reconstruction from noiseless samples were derived, the presence of noise makes sampling set selection combinatorial and NP-hard in general …”
Volltext

Machine learning based energy-free structure predictions of molecules, transition states, and solids von Lemm, Dominik, von Rudorff, Guido Falk, von Lilienfeld, O. Anatole

“… Conventionally, force-fields or ab initio methods determine structure through energy minimization, which is either approximate or computationally demanding …”
Volltext

Statistical learning problem of artificial neural network to control roofing process von Lapidus, Azariy, Makarov, Aleksandr

“… ANN learning is the main stage of its development. A key question for supervised learning is how many number of training examples we need to approximate the true relationship between network inputs and output with the desired accuracy …”
Volltext

Algorithm for sparse representation minimizing mean square error of power spectrograms von Tanaka, Yuma, Ogawa, Takahiro, Haseyama, Miki

“… Sparse representation is an idea to approximate a target signal by a linear combination of a small number of sample signals, and it is utilized in various research fields …”
Volltext

Efficient and accurate approximate Bayesian inference with an application to insurance data von Streftaris, George, Worton, Bruce J.

“… An approximate Gibbs sampling method and an exact independence-type Metropolis–Hastings algorithm are derived, based on a log-normal/gamma mixture density that closely approximates the conditional distribution of the Poisson parameters …”
Volltext

Group Distributionally Robust Dataset Distillation with Risk Minimization von Vahidian, Saeed, Wang, Mingyu, Gu, Jianyang, Kungurtsev, Vyacheslav, Jiang, Wei, Chen, Yiran

“… However, targeting the training dataset must be thought of as auxiliary in the same sense that the training set is an approximate substitute for the population distribution, and the latter is the data …”
Volltext

An optimal control framework for adaptive neural ODEs von Aghili, Joubine, Mula, Olga

“… The learning task consists in finding the ODE parameters as the optimal values of a sampled loss minimization problem …”
Volltext