Peva Blanchard

Byzantine-Tolerant Machine Learning

2017 · arXiv (Cornell University)

The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machine learning frameworks have largely ignored the possibility …

On Monotonicity in AI Alignment

2025 · arXiv (Cornell University)

Comparison-based preference learning has become central to the alignment of AI models with human preferences. However, these methods may behave counterintuitively. After empirically observing that, when accounting for a preference for response $y$ over $z$, …