Vectorized 1-Nearest-Neighbor in NumPy and Its Equivalence to a Linear Layer
Company: OpenAI
Role: Machine Learning Engineer
Category: Machine Learning
Difficulty: hard
Interview Round: Onsite
Overview: Implement a 1-nearest-neighbor classifier in NumPy using only vectorized operations, then show that finding the nearest training point is equivalent to an argmax over a linear layer W x + b built from the training data. It tests broadcasting, the expanded L2 distance, memory limits and numerical stability.