4 papers
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…
Active Learning for Neurosymbolic Program Synthesis
Celeste Barnaby, Qiaochu Chen, Ramya Ramalingam +2
The goal of active learning for program synthesis is to synthesize the desired program by asking targeted questions that minimize user interaction. While prior work has explored ac…
A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
Stephen Mell, Botong Zhang, David Mell +5
Modern large language models (LLMs) are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for…
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…