Search Results for author:
Found 10 papers, 4 papers with code
It's All in the Mix: Wasserstein Machine Learning with Mixed Features
A key challenge in this context is the presence of estimation errors in the prediction models, which tend to be amplified by the subsequent optimization model -- a phenomenon that is often referred to as the Optimizer's Curse or the Error-Maximization Effect of Optimization.
Streamlining Energy Transition Scenarios to Key Policy Decisions
Uncertainties surrounding the energy transition often lead modelers to present large sets of scenarios that are challenging for policymakers to interpret and act upon.
Differential Privacy via Distributionally Robust Optimization
We show that the problem affords a strong dual, and we exploit this duality to develop converging hierarchies of finite-dimensional upper and lower bounding problems.
Robust Phi-Divergence MDPs
In recent years, robust Markov decision processes (MDPs) have emerged as a prominent modeling framework for dynamic decision problems affected by uncertainty.
Partial Policy Iteration for L1-Robust Markov Decision Processes
Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities.
On Linear Optimization over Wasserstein Balls
In this technical note we prove that the Wasserstein ball is weakly compact under mild conditions, and we offer necessary and sufficient conditions for the existence of optimal solutions.
Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation
The likelihood function is a fundamental component in Bayesian statistics.
Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization
A fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions.
Fast Bellman Updates for Robust MDPs
The first algorithm uses a homotopy continuation method to compute updates for L1-constrained s, a-rectangular ambiguity sets.
Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization
Plain vanilla K-means clustering has proven to be successful in practice, yet it suffers from outlier sensitivity and may produce highly unbalanced clusters.
