Algorithms and Theory

Multi-touch attribution (MTA) estimates the relative contributions of the multiple ads a user may see prior to any observed conversions. Increasingly, advertisers also want to bid based on these attributions, increasing bids on ads that drive more conversions. We describe two requirements for an MTA system to be suitable for this application: First, it must be able to handle continuously...

In machine learning, a question of great interest is understanding what examples are challenging for a model to classify. Identifying atypical examples helps inform safe deployment of models, isolates examples that require further human inspection, and provides interpretability into model behavior. In this work, we propose Variance of Gradients (VOG) as a proxy metric for detecting outliers in...

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably well. An emerging paradigm for describing this unexpected behavior is in terms of a double descent curve, in which increasing a model's capacity causes its...

A two-sided market consists of two sets of agents, each of whom have preferences over the other (Airbnb, Upwork, Lyft, Uber, etc.). We propose and analyze a repeated matching problem, where each time step consists of a single match, and our goal is to ensure fairness with respect to the cumulative allocations over an infinite time horizon. We prove several positive results, our main one being...