220 citations · 724 across the 45 of their papers we have counts for
5 papers · 2 filters
Regularization via Mass Transportation
Soroosh Shafieezadeh-Abadeh, Daniel Kuhn, Peyman Mohajerin Esfahani
The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the predictio…
Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization
Napat Rujeerapaiboon, Kilian Schindler, Daniel Kuhn +1
Plain vanilla K-means clustering has proven to be successful in practice, yet it suffers from outlier sensitivity and may produce highly unbalanced clusters. To mitigate both short…
From Data to Decisions: Distributionally Robust Optimization is Optimal
Bart P. G. Van Parys, Peyman Mohajerin Esfahani, Daniel Kuhn
We study stochastic programs where the decision-maker cannot observe the distribution of the exogenous uncertainties but has access to a finite set of independent samples from this…
From Infinite to Finite Programs: Explicit Error Bounds with Applications to Approximate Dynamic Programming
Peyman Mohajerin Esfahani, Tobias Sutter, Daniel Kuhn +1
We consider linear programming (LP) problems in infinite dimensional spaces that are in general computationally intractable. Under suitable assumptions, we develop an approximation…
Scenario Reduction Revisited: Fundamental Limits and Guarantees
Napat Rujeerapaiboon, Kilian Schindler, Daniel Kuhn +1
The goal of scenario reduction is to approximate a given discrete distribution with another discrete distribution that has fewer atoms. We distinguish continuous scenario reduction…