activity
20242026
collaborators
Showing 2024Show all

6 papers · 1 filter

cs.LG2024

Choice Between Partial Trajectories: Disentangling Goals from Beliefs

Henrik Marklund, Benjamin Van Roy

As AI agents generate increasingly sophisticated behaviors, manually encoding human preferences to guide these agents becomes more challenging. To address this, it has been suggest…

cs.LG2024

Aligning AI Agents via Information-Directed Sampling

Hong Jun Jeon, Benjamin Van Roy

The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing fr…

cs.LG2024

The Need for a Big World Simulator: A Scientific Challenge for Continual Learning

Saurabh Kumar, Hong Jun Jeon, Alex Lewandowski +1

The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot s…

cs.LG2024

Information-Theoretic Foundations for Neural Scaling Laws

Hong Jun Jeon, Benjamin Van Roy

Neural scaling laws aim to characterize how out-of-sample error behaves as a function of model and training dataset size. Such scaling laws guide allocation of a computational reso…

cs.LG2024

Adaptive Crowdsourcing Via Self-Supervised Learning

Anmol Kagrecha, Henrik Marklund, Benjamin Van Roy +2

Common crowdsourcing systems average estimates of a latent quantity of interest provided by many crowdworkers to produce a group estimate. We develop a new approach -- predict-each…

cs.LG2024

An Information-Theoretic Analysis of In-Context Learning

Hong Jun Jeon, Jason D. Lee, Qi Lei +1

Previous theoretical results pertaining to meta-learning on sequences build on contrived assumptions and are somewhat convoluted. We introduce new information-theoretic tools that…