English
Related papers

Related papers: Set structured global empirical risk minimizers ar…

200 papers

In the past years statistical physics has been successfully applied for complex networks modelling. In particular, it has been shown that the maximum entropy principle can be exploited in order to construct graph ensembles for real-world…

Empirical risk minimization (ERM) is ubiquitous in machine learning and underlies most supervised learning methods. While there has been a large body of work on algorithms for various ERM problems, the exact computational complexity of ERM…

Computational Complexity · Computer Science 2017-04-11 Arturs Backurs , Piotr Indyk , Ludwig Schmidt

Despite empirical risk minimization (ERM) is widely applied in the machine learning community, its performance is limited on data with spurious correlation or subpopulation that is introduced by hidden attributes. Existing literature…

Machine Learning · Computer Science 2024-12-18 Hongyu Shen , Zhizhen Zhao

We present a framework for the theoretical analysis of ensembles of low-complexity empirical risk minimisers trained on independent random compressions of high-dimensional data. First we introduce a general distribution-dependent…

Machine Learning · Computer Science 2021-06-03 Henry W. J. Reeve , Ata Kaban

Many machine learning tasks can be formulated as Regularized Empirical Risk Minimization (R-ERM), and solved by optimization algorithms such as gradient descent (GD), stochastic gradient descent (SGD), and stochastic variance reduction…

Machine Learning · Statistics 2016-09-28 Qi Meng , Yue Wang , Wei Chen , Taifeng Wang , Zhi-Ming Ma , Tie-Yan Liu

Expectation Maximization (EM) is among the most popular algorithms for estimating parameters of statistical models. However, EM, which is an iterative algorithm based on the maximum likelihood principle, is generally only guaranteed to find…

Statistics Theory · Mathematics 2016-08-30 Ji Xu , Daniel Hsu , Arian Maleki

Envelope method was recently proposed as a method to reduce the dimension of responses in multivariate regressions. However, when there exists missing data, the envelope method using the complete case observations may lead to biased and…

Methodology · Statistics 2021-03-25 Linquan Ma , Lan Liu , Wei Yang

We study the approximability of instances of the minimum entropy set cover problem, parameterized by the average frequency of a random element in the covering sets. We analyze an algorithm combining a greedy approach with another one biased…

Data Structures and Algorithms · Computer Science 2012-08-01 Cosmin Bonchis , Gabriel Istrate

Maximum entropy models provide the least constrained probability distributions that reproduce statistical properties of experimental datasets. In this work we characterize the learning dynamics that maximizes the log-likelihood in the case…

Disordered Systems and Neural Networks · Physics 2016-09-21 Ulisse Ferrari

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

The EM algorithm is one of the most popular algorithm for inference in latent data models. The original formulation of the EM algorithm does not scale to large data set, because the whole data set is required at each iteration of the…

Machine Learning · Statistics 2019-10-29 Belhal Karimi , Hoi-To Wai , Eric Moulines , Marc Lavielle

The maximum entropy principle (MEP) apparently allows us to derive, or justify, fundamental results of equilibrium statistical mechanics. Because of this, a school of thought considers the MEP as a powerful and elegant way to make…

Statistical Mechanics · Physics 2015-12-09 Gennaro Auletta , Lamberto Rondoni , Angelo Vulpiani

This paper develops several interesting, significant, and interconnected approaches to nonparametric or semi-parametric statistical inferences. The overwhelmingly favoured maximum likelihood estimator (MLE) under parametric model is…

Statistics Theory · Mathematics 2023-03-30 Haodi Liang , Jiahua Chen

The universal learning framework has been developed to obtain guarantees on the learning rates that hold for any fixed distribution, which can be much faster than the ones uniformly hold over all the distributions. Given that the Empirical…

Machine Learning · Statistics 2025-07-16 Steve Hanneke , Mingyue Xu

A risk measure that is consistent with the second-order stochastic dominance and additive for sums of independent random variables can be represented as a weighted entropic risk measure (WERM). The expected utility maximization problem with…

Mathematical Finance · Quantitative Finance 2021-12-07 Jianming Xia

This paper investigates the optimal ergodic sublinear convergence rate of the relaxed proximal point algorithm for solving monotone variational inequality problems. The exact worst case convergence rate is computed using the performance…

Optimization and Control · Mathematics 2019-07-15 Guoyong Gu , Junfeng Yang

We show that empirical risk minimization procedures and regularized empirical risk minimization procedures satisfy nonexact oracle inequalities in an unbounded framework, under the assumption that the class has a subexponential envelope…

Statistics Theory · Mathematics 2012-06-06 Guillaume Lecué , Shahar Mendelson

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

Machine Learning · Computer Science 2022-08-16 Kenneth Bogert , Yikang Gui , Prashant Doshi

Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…

Machine Learning · Statistics 2022-06-16 Brian Lucena

An inverse modeling technique is introduced that combines elements of coupled logistic map models and wavelet analysis for the purpose of analyzing partial synchronization states in high-dimensional systems. Using Embedded Complex Logistic…

Adaptation and Self-Organizing Systems · Physics 2007-05-23 Sandy Shaw