[KİTAP][B] Statistical foundations of data science
Statistical Foundations of Data Science gives a thorough introduction to commonly used
statistical models, contemporary statistical machine learning techniques and algorithms …
statistical models, contemporary statistical machine learning techniques and algorithms …
Sample complexity of sample average approximation for conditional stochastic optimization
In this paper, we study a class of stochastic optimization problems, referred to as the
conditional stochastic optimization (CSO), in the form of x∈XE_ξf_ξ(E_η|ξg_η(x,ξ)), which …
conditional stochastic optimization (CSO), in the form of x∈XE_ξf_ξ(E_η|ξg_η(x,ξ)), which …
Bilevel cutting-plane algorithm for cardinality-constrained mean-CVaR portfolio optimization
This paper studies mean-risk portfolio optimization models using the conditional value-at-
risk (CVaR) as a risk measure. We also employ a cardinality constraint for limiting the …
risk (CVaR) as a risk measure. We also employ a cardinality constraint for limiting the …
Diametrical risk minimization: Theory and computations
MD Norton, JO Royset - Machine Learning, 2023 - Springer
The theoretical and empirical performance of Empirical Risk Minimization (ERM) often
suffers when loss functions are poorly behaved with large Lipschitz moduli and spurious …
suffers when loss functions are poorly behaved with large Lipschitz moduli and spurious …
Logarithmic sample bounds for Sample Average Approximation with capacity-or budget-constraints
Abstract Sample Average Approximation (SAA) is used to approximately solve stochastic
optimization problems. In practice, SAA requires much fewer samples than predicted by …
optimization problems. In practice, SAA requires much fewer samples than predicted by …
New Sample Complexity Bounds for (Regularized) Sample Average Approximation in Several Heavy-Tailed, Non-Lipschitzian, and High-Dimensional Cases
H Liu, J Tong - arxiv preprint arxiv:2401.00664, 2024 - arxiv.org
We study the sample complexity of sample average approximation (SAA) and its simple
variations, referred to as the regularized SAA (RSAA), in solving convex and strongly convex …
variations, referred to as the regularized SAA (RSAA), in solving convex and strongly convex …
An Uncertain Optimization Method Based on Adaptive Discrete Approximation Rejection Sampling for Stochastic Programming with Incomplete Knowledge of …
B Fang, Z Dong, C Zhao, Z Liu, J Wang - Arabian Journal for Science and …, 2023 - Springer
Stochastic programming has been widely used in various application scenarios and
theoretical research works. However, these excellent methods depend on specific explicit …
theoretical research works. However, these excellent methods depend on specific explicit …
General Feasibility Bounds for Sample Average Approximation via Vapnik--Chervonenkis Dimension
We investigate the feasibility of sample average approximation (SAA) for general stochastic
optimization problems, including two-stage stochastic programs without relatively complete …
optimization problems, including two-stage stochastic programs without relatively complete …
High-dimensional learning under approximate sparsity with applications to nonsmooth estimation and regularized neural networks
High-dimensional statistical learning (HDSL) has wide applications in data analysis,
operations research, and decision making. Despite the availability of multiple theoretical …
operations research, and decision making. Despite the availability of multiple theoretical …
[PDF][PDF] Metric entropy-free sample complexity bounds for sample average approximation in convex stochastic programming
H Liu, J Tong - arxiv preprint arxiv:2401.00664, 2024 - arxiv.org
This paper studies sample average approximation (SAA) in solving convex or strongly
convex stochastic programming (SP) problems. Under some common regularity conditions …
convex stochastic programming (SP) problems. Under some common regularity conditions …