collaborators

6 papers

cs.LG2026

Defensive Boosting for Online Probabilistic Forecasting

Georgy Noarov, Aaron Roth

We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class , we would like to e…

cs.LG2026

Optimal Deterministic Multicalibration and Omniprediction

Georgy Noarov, Aaron Roth

A model is multicalibrated on a collection of group weights if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweight…

cs.GT2026

Prior-Agnostic Incentive-Compatible Exploration

Ramya Ramalingam, Osbert Bastani, Aaron Roth

In bandit settings, optimizing long-term regret metrics requires exploration, which corresponds to sometimes taking myopically sub-optimal actions. When a long-lived principal mere…

stat.ML2025

Robust Decision Making with Partially Calibrated Forecasts

Shayan Kiyani, Hamed Hassani, George Pappas +1

Calibration has emerged as a foundational goal in ``trustworthy machine learning'', in part because of its strong decision theoretic semantics. Independent of the underlying distri…

cs.LG2025

The Relationship between No-Regret Learning and Online Conformal Prediction

Ramya Ramalingam, Shayan Kiyani, Aaron Roth

Existing algorithms for online conformal prediction -- guaranteeing marginal coverage in adversarial settings -- are variants of online gradient descent (OGD), but their analyses o…

cs.LG2025

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

Shayan Kiyani, George Pappas, Aaron Roth +1

A fundamental question in data-driven decision making is how to quantify the uncertainty of predictions in ways that can usefully inform downstream action. This interface between p…