Timezone: »

 
Poster
Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses
Sanket Shah · Kai Wang · Bryan Wilder · Andrew Perrault · Milind Tambe

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #112
in Poster Session 3 »

Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to perform better \textit{on that specific task}. The main technical challenge associated with DFL is that it requires being able to differentiate through the optimization problem, which is difficult due to discontinuous solutions and other challenges. Past work has largely gotten around this this issue by \textit{handcrafting} task-specific surrogates to the original optimization problem that provide informative gradients when differentiated through. However, the need to handcraft surrogates for each new task limits the usability of DFL. In addition, there are often no guarantees about the convexity of the resulting surrogates and, as a result, training a predictive model using them can lead to inferior local optima. In this paper, we do away with surrogates altogether and instead \textit{learn} loss functions that capture task-specific information. To the best of our knowledge, ours is the first approach that entirely replaces the optimization component of decision-focused learning with a loss that is automatically learned. Our approach (a) only requires access to a black-box oracle that can solve the optimization problem and is thus \textit{generalizable}, and (b) can be \textit{convex by construction} and so can be easily optimized over. We evaluate our approach on three resource allocation problems from the literature and find that our approach outperforms learning without taking into account task-structure in all three domains, and even hand-crafted surrogates from the literature.

Keywords: Optimization · machine learning · prediction · Decision-Focused Learning
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Sanket Shah (Harvard University)
Sanket Shah

I am a third-year PhD student at Harvard University advised by Prof. Milind Tambe. My current work focuses on Decision-Focused Learning, a paradigm for tailoring a predictive model for a downstream optimization task that uses its predictions.

Kai Wang (Harvard University)
Bryan Wilder (Harvard University)
Andrew Perrault (The Ohio State University)
Milind Tambe (Harvard University/Google Research)

More from the Same Authors