Timezone: »

Adaptive Sampling for Stochastic Risk-Averse Learning
Sebastian Curi · Kfir Y. Levy · Stefanie Jegelka · Andreas Krause

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1451
In high-stakes machine learning applications, it is crucial to not only perform well {\em on average}, but also when restricted to {\em difficult} examples. To address this, we consider the problem of training models in a risk-averse manner. We propose an adaptive sampling algorithm for stochastically optimizing the {\em Conditional Value-at-Risk (CVaR)} of a loss distribution, which measures its performance on the $\alpha$ fraction of most difficult examples. We use a distributionally robust formulation of the CVaR to phrase the problem as a zero-sum game between two players, and solve it efficiently using regret minimization. Our approach relies on sampling from structured Determinantal Point Processes (DPPs), which enables scaling it to large data sets. Finally, we empirically demonstrate its effectiveness on large-scale convex and non-convex learning tasks.

Author Information

Sebastian Curi (ETH Zürich)
Kfir Y. Levy (Technion)
Stefanie Jegelka (MIT)
Andreas Krause (ETH Zurich)

More from the Same Authors