3 papers
stat.ML2025
Infinite Neural Operators: Gaussian processes on functions
Daniel Augusto de Souza, Yuchen Zhu, Harry Jake Cunningham +3
A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over their outputs. These relationships provide both…
cs.LG2024
When Can Proxies Improve the Sample Complexity of Preference Learning?
Yuchen Zhu, Daniel Augusto de Souza, Zhengyan Shi +4
We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as…
stat.ML2024
Structured Learning of Compositional Sequential Interventions
Jialin Yu, Andreas Koukorinis, Nicolò Colombo +2
We consider sequential treatment regimes where each unit is exposed to combinations of interventions over time. When interventions are described by qualitative labels, such as "clo…