Risk Bounds and Calibration for a Smart Predict-then-Optimize Method
Dec 6, 2021
Speakers
Heyuan Liu
Speaker · 0 followers
Paul Grigas
Speaker · 0 followers
About
The predict-then-optimize framework is fundamental in practical stochastic decision-making problems: first predict unknown parameters of an optimization model, then solve the problem using the predicted values. A natural loss function in this setting is defined by measuring the decision error induced by the predicted parameters, which was named the Smart Predict-then-Optimize (SPO) loss by Elmachtoub and Grigas [2021]. Since the SPO loss is typically nonconvex and possibly discontinuous, Elmachtoub and Grigas [2021] introduced a convex surrogate, called the SPO+ loss, that importantly accounts for the underlying structure of the optimization model. In this paper, we greatly expand upon the consistency results for the SPO+ loss provided by Elmachtoub and Grigas [2021]. We develop risk bounds and uniform calibration results for the SPO+ loss relative to the SPO loss, which provide a quantitative way to transfer the excess surrogate risk to excess true risk. By combining our risk bounds with generalization bounds, we show that the empirical minimizer of the SPO+ loss achieves low excess true risk with high probability. We first demonstrate these results in the case when the feasible region of the underlying optimization problem is a polyhedron, and then we show that the results can be strengthened substantially when the feasible region is a level set of a strongly convex function. We perform experiments to empirically demonstrate the strength of the SPO+ surrogate, as compared to standard ℓ_1 and squared ℓ_2 prediction error losses, on portfolio allocation and cost-sensitive multi-class classification problems.The predict-then-optimize framework is fundamental in practical stochastic decision-making problems: first predict unknown parameters of an optimization model, then solve the problem using the predicted values. A natural loss function in this setting is defined by measuring the decision error induced by the predicted parameters, which was named the Smart Predict-then-Optimize (SPO) loss by Elmachtoub and Grigas [2021]. Since the SPO loss is typically nonconvex and possibly discontinuous, Elmacht…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Offline Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Is Importance Weighting Incompatible with Interpolating Classifiers?
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving Cars
Watch later
Mingze Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Techniques and conclusion
Watch later
Lilian Weng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
Watch later
Yufei Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation
Watch later
Arno Solin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%