Search Results for author:
Found 10 papers, 3 papers with code
Three Factors Influencing Minima in SGD
In particular we find that the ratio of learning rate to batch size is a key determinant of SGD dynamics and of the width of the final minima, and that higher values of the ratio lead to wider minima and often better generalization.
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
When studying the SGD dynamics in relation to the sharpest directions in this initial phase, we find that the SGD step is large compared to the curvature and commonly fails to minimize the loss along the sharpest directions.
Generalizing from a few environments in safety-critical reinforcement learning
Before deploying autonomous agents in the real world, we need to be confident they will perform safely in novel situations.
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
From our comparison we conclude that some current techniques which solve benchmarks such as UCI `overfit' their uncertainty to the dataset---when evaluated on our benchmark these underperform in comparison to simpler baselines.
Imitating Interactive Intelligence
These evaluations convincingly demonstrate that interactive training and auxiliary losses improve agent behaviour beyond what is achieved by supervised learning of actions alone.
Alignment of Language Agents
For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want.
Safe Deep RL in 3D Environments using Human Feedback
In this paper we answer this question in the affirmative, using ReQueST to train an agent to perform a 3D first-person object collection task using data entirely from human contractors.
Discovering Agents
Causal models of agents have been used to analyse the safety aspects of machine learning systems.
Explaining grokking through circuit efficiency
One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, transition to perfect generalisation.
Challenges with unsupervised LLM knowledge discovery
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent.
