56 citations · 62 across the 12 of their papers we have counts for
10 papers · 1 filter
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…
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…
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…
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…
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…
Continual Learning as Computationally Constrained Reinforcement Learning
Saurabh Kumar, Henrik Marklund, Ashish Rao +4
An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills over a long lifetime could advance the frontier of artificial intelligence capabilities…
An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws
Hong Jun Jeon, Benjamin Van Roy
We study the compute-optimal trade-off between model and training data set sizes for large neural networks. Our result suggests a linear relation similar to that supported by the e…
Is Stochastic Gradient Descent Near Optimal?
Yifan Zhu, Hong Jun Jeon, Benjamin Van Roy
The success of neural networks over the past decade has established them as effective models for many relevant data generating processes. Statistical theory on neural networks indi…
An Information-Theoretic Framework for Supervised Learning
Hong Jun Jeon, Yifan Zhu, Benjamin Van Roy
Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to…
Reward-rational (implicit) choice: A unifying formalism for reward learning
Hong Jun Jeon, Smitha Milli, Anca D. Dragan
It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. T…