Ambuj Tewari

Continuum Transformers Perform In-Context Learning by Operator Gradient Descent

A Greedy PDE Router for Blending Neural Operators and Classical Methods

Latency-Aware Contextual Bandit: Application to Cryo-EM Data Collection

Leveraging Offline Data in Linear Latent Contextual Bandits

Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

On the Benefits of Active Data Collection in Operator Learning

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

A Theoretical Framework for Partially-Observed Reward States in RLHF

Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators