10 citations · 22 across the 5 of their papers we have counts for
7 papers
Revisiting scaling laws for reward optimization
Ali Aouad, Aymane El Gadarri, Vivek F. Farias
Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL-divergence budget relative to…
The Sign Estimator: LLM Alignment in the Face of Choice Heterogeneity
Ali Aouad, Aymane El Gadarri, Vivek F. Farias
Traditional LLM alignment methods are vulnerable to heterogeneity in human preferences. Fitting a naïve probabilistic model to pairwise comparison data (say over prompt-completion…
The Pandora's Box Problem with Sequential Inspections
Ali Aouad, Jingwei Ji, Yaron Shaposhnik
The Pandora's box problem (Weitzman 1979) is a core model in economic theory that captures an agent's (Pandora's) search for the best alternative (box). We study an important gener…
A Nonparametric Framework for Online Stochastic Matching with Correlated Arrivals
Ali Aouad, Will Ma
The design of online algorithms for matching markets and revenue management settings is usually bound by the assumption that the demand process is formed by a fixed-length sequence…
Representing Random Utility Choice Models with Neural Networks
Ali Aouad, Antoine Désir
Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) fr…
An Approximate Dynamic Programming Approach to The Incremental Knapsack Problem
Ali Aouad, Danny Segev
We study the incremental knapsack problem, where one wishes to sequentially pack items into a knapsack whose capacity expands over a finite planning horizon, with the objective of…
Market Segmentation Trees
Ali Aouad, Adam N. Elmachtoub, Kris J. Ferreira +1
We seek to provide an interpretable framework for segmenting users in a population for personalized decision-making. We propose a general methodology, Market Segmentation Trees (MS…