Results 21 to 30 of about 33 (31)
Optimal Learning via Moderate Deviations Theory
, 2023 This paper proposes a statistically optimal approach for learning a function value using a confidence interval in a wide range of models, including general non-parametric estimation of an expected loss described as a stochastic programming problem or ...
Ganguly, Arnab, Sutter, Tobias
core
, 2023 Understanding the implicit regularization imposed by neural network architectures and gradient based optimization methods is a key challenge in deep learning and AI.
Antun, Vegard +2 more
core
Outer Approximation for Mixed-Integer Nonlinear Robust Optimization [PDF]
Currently, few approaches are available for mixed-integer nonlinear robust optimization. Those that do exist typically either require restrictive assumptions on the problem structure or do not guarantee robust protection.
Kuchlbauer, Martina +2 more
core +2 more sources
Robust static and dynamic maximum flows [PDF]
We study the robust maximum flow problem and the robust maximum flow over time problem where a given number of arcs Γmay fail or may be delayed. Two prominent models have been introduced for these problems: either one assigns flow to arcs fulfilling weak
Biefel, Christian +3 more
core +2 more sources
Distributionally Robust Markov Decision Processes and their Connection to Risk Measures
, 2020 We consider robust Markov Decision Processes with Borel state and action spaces, unbounded cost and finite time horizon. Our formulation leads to a Stackelberg game against nature.
Bäuerle, Nicole, Glauner, Alexander
core
Innovasjon i norsk næringsliv 2010-2012 [PDF]
, 2015 Det totale bildet av innovasjonsaktiviteter viser relativt små endringer i perioden 2010-2012 sammenlignet med den forrige innovasjonsundersøkelsen for 2008- 2010.
Berrios, Claudia, Wilhelmsen, Lars
core
Adjustable Robust Nonlinear Network Design under Demand Uncertainties
We study network design problems for nonlinear and nonconvex flow models under demand uncertainties. To this end, we apply the concept of adjustable robust optimization to compute a network design that admits a feasible transport for all, possibly ...
Grübel, Julia +2 more
core
Accelerating Ill-conditioned Hankel Matrix Recovery via Structured Newton-like Descent
This paper studies the robust Hankel recovery problem, which simultaneously removes the sparse outliers and fulfills missing entries from the partial observation.
Cai, HanQin +3 more
core
Word Order and Information Structure in Old Irish [PDF]
, 2020 BUDASSI, Marco, ROMA, ELISA
core +1 more source