Search Results for author:
Found 7 papers, 0 papers with code
An Information-Theoretic Analysis of In-Context Learning
Previous theoretical results pertaining to meta-learning on sequences build on contrived assumptions and are somewhat convoluted.
Adaptive Crowdsourcing Via Self-Supervised Learning
Common crowdsourcing systems average estimates of a latent quantity of interest provided by many crowdworkers to produce a group estimate.
Continual Learning as Computationally Constrained Reinforcement Learning
The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning.
An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws
For a particular learning model inspired by barron 1993, we establish an upper bound on the minimal information-theoretically achievable expected error as a function of model and data set sizes.
Is Stochastic Gradient Descent Near Optimal?
However, existing computational theory suggests that, even for single-hidden-layer teacher networks, to attain small error for all such teacher networks, the computation required to achieve this sample complexity is intractable.
An Information-Theoretic Framework for Supervised Learning
For a particular prior distribution on weights, we establish sample complexity bounds that are simultaneously width independent and linear in depth.
Reward-rational (implicit) choice: A unifying formalism for reward learning
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.
