4 papers
Optimal Empirical Risk Minimization under Temporal Distribution Shifts
Yujin Jeong, Ramesh Johari, Dominik Rothenhäusler +1
Temporal distribution shifts pose a key challenge for machine learning models trained and deployed in dynamically evolving environments. This paper introduces RIDER (RIsk minimizat…
The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Games
Lyle Goodyear, Rachel Guo, Ramesh Johari
Large Language Models (LLMs) have shown promise as decision-makers in dynamic settings, but their stateless nature necessitates creating a natural language representation of histor…
Switchback Price Experiments with Forward-Looking Demand
Yifan Wu, Ramesh Johari, Vasilis Syrgkanis +1
We consider a retailer running a switchback experiment for the price of a single product, with infinite supply. In each period, the seller chooses a price from a set of predefi…
When Does Interference Matter? Decision-Making in Platform Experiments
Ramesh Johari, Hannah Li, Anushka Murthy +1
This paper investigates decision-making in A/B experiments for online platforms and marketplaces. In such settings, due to constraints on inventory, A/B experiments typically lead…