Richa Rastogi — accepted AI-conference papers

2025

MultiScale Contextual Bandits for Long Term Objectives

Richa Rastogi, Yuta Saito, Thorsten Joachims

NeurIPS 2025poster

The feedback that AI systems (e.g., recommender systems, chatbots) collect from user interactions is a crucial source of training data. While short-term feedback (e.g., clicks, engagement) is widely used for training, there is ample evidence that optimizing short-term feedback does not necessarily a…

Cited by 0 Source ↗Scholar ↗

2023

Semi-Parametric Inducing Point Networks and Neural Processes

Richa Rastogi, Yair Schiff, Alon Hacohen, Zhaozhi Li, Ian Lee, Yuntian Deng +2

ICLR 2023poster

We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-parametric architectures are typically more compact than parametric models, but their computational complexity is often qu…

Cited by 10 Source ↗PDF ↗Scholar ↗