Want to make decision recommendations that align with human intuition for better adoption? Check out our new #NeurIPS paper conformal inverse optimization (https://t.co/gmVS73jl5S). Extended version on SSRN now (https://t.co/ZQEvWfSsDo). Feedback welcome!
When I first moved to Toronto, I read a paper about LTS from @shoshannasaxe. I cold called asking if we could explore TO specific research. The partnership has been amazing. @mbonsma and @bolin0812 are guiding us on how „best“ to invest in #biketo. Read about the work below:
If you're at #NeurIPS2022 and interested in ML-for-Optimization, please check out my students and collaborators' poster presentations; a brief overview ⬇️
1/8) 87% of AI projects fail to hit production, 96% have data problems & 51% underestimate how much data they need.
Our #NeurIPS2022 paper proposes learning & optimizing data collection!
w/ @james_r_lucas@ALVAREZ_JOSEM@FidlerSanja@MarcTLaw
Webpage: https://t.co/q7M4fjdn3s
As a special case, the model also generalizes two-stage stochastic programs. We hope this new methodology can be a useful tool for OR researchers and practitioners who seek to apply optimization methods at an impactful scale.
Now published: The Impact of COVID-19 Cycling Infrastructure on Low-Stress Cycling Accessibility: A Case Study in the City of Toronto | Published in Findings https://t.co/AcWWRvzMKl