16 papers
Narrowing the Collaboration Gap, Probably
Mirah Shi, Marcel Hussing, Ira Globus-Harris +3
Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents concisely communicate in a wa…
Groupwise Distortion Guarantees for Preference-Based Alignment
Jacob Brodkey, Roberto Tamez, Aaron Roth
Preference-based alignment methods such as reinforcement learning from human feedback (RLHF) and Nash learning from human feedback (NLHF) aggregate pairwise preferences to learn an…
Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control
Natalie Collina, Surbhi Goel, Aaron Roth +1
Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If the agent is not fully aligned,…
The Sample Complexity of Multicalibration
Natalie Collina, Jiuyao Lu, Georgy Noarov +1
We study the minimax sample complexity of multicalibration in the batch setting. A learner observes i.i.d. samples from an unknown distribution and must output a (possibly rand…
Personalization Aids Pluralistic Alignment Under Competition
Natalie Collina, Surbhi Goel, Aaron Roth +1
Can competition among misaligned AI providers yield aligned outcomes for a diverse population of users, and what role does model personalization play? We study a setting where mult…
Emergent Alignment via Competition
Natalie Collina, Surbhi Goel, Aaron Roth +2
Aligning AI systems with human values remains a fundamental challenge, but does our inability to create perfectly aligned models preclude obtaining the benefits of alignment? We st…
Conformal Language Model Reasoning with Coherent Factuality
Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji +2
Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factu…
Collaborative Prediction: Tractable Information Aggregation via Agreement
Natalie Collina, Ira Globus-Harris, Surbhi Goel +3
We give efficient "collaboration protocols" through which two parties, who observe different features about the same instances, can interact to arrive at predictions that are more…
Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses
Jiuyao Lu, Aaron Roth, Mirah Shi
We define "decision swap regret" which generalizes both prediction for downstream swap regret and omniprediction, and give algorithms for obtaining it for arbitrary multi-dimension…
Tractable Agreement Protocols
Natalie Collina, Surbhi Goel, Varun Gupta +1
We present an efficient reduction that converts any machine learning algorithm into an interactive protocol, enabling collaboration with another party (e.g., a human) to achieve co…
The Value of Ambiguous Commitments in Multi-Follower Games
Natalie Collina, Rabanus Derr, Aaron Roth
We study games in which a leader makes a single commitment, and then multiple followers (each with a different utility function) respond. In particular, we study ambiguous commitme…
The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review
Buxin Su, Jiayao Zhang, Natalie Collina +6
We conducted an experiment during the review process of the 2023 International Conference on Machine Learning (ICML), asking authors with multiple submissions to rank their papers…
Repeated Contracting with Multiple Non-Myopic Agents: Policy Regret and Limited Liability
Natalie Collina, Varun Gupta, Aaron Roth
We study a repeated contracting setting in which a Principal adaptively chooses amongst Agents at each of rounds. The Agents are non-myopic, and so a mechanism for the Prin…
An Elementary Predictor Obtaining Distance to Calibration
Eshwar Ram Arunachaleswaran, Natalie Collina, Aaron Roth +1
Blasiok et al. [2023] proposed distance to calibration as a natural measure of calibration error that unlike expected calibration error (ECE) is continuous. Recently, Qiao and Zhen…
Forecasting for Swap Regret for All Downstream Agents
Aaron Roth, Mirah Shi
We study the problem of making predictions so that downstream agents who best respond to them will be guaranteed diminishing swap regret, no matter what their utility functions are…
Efficient Prior-Free Mechanisms for No-Regret Agents
Natalie Collina, Aaron Roth, Han Shao
We study a repeated Principal Agent problem between a long lived Principal and Agent pair in a prior free setting. In our setting, the sequence of realized states of nature may be…