13 papers
Offline Constrained Reinforcement Learning under Partial Data Coverage
Seokmin Ko, Ambuj Tewari, Kihyuk Hong
We study offline constrained reinforcement learning with general function approximation in discounted constrained Markov decision processes. Prior methods either require full data…
A Greedy PDE Router for Blending Neural Operators and Classical Methods
Sahana Rayan, Yash Patel, Ambuj Tewari
When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency…
Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
Yash Patel, Unique Subedi, Ambuj Tewari
We consider the problem of learning the evolution operator for the time-dependent Schrödinger equation, where the Hamiltonian may vary with time. Existing neural network-based sur…
A Training-free Method for LLM Text Attribution
Tara Radvand, Mojtaba Abdolmaleki, Mohamed Mostagir +1
Verifying the provenance of content is crucial to the functioning of many organizations, e.g., educational institutions, social media platforms, and firms. This problem is becoming…
Distribution-Free Robust Predict-Then-Optimize in Function Spaces
Yash Patel, Ambuj Tewari
The need to rapidly solve PDEs in engineering design workflows has spurred the rise of neural surrogate models. In particular, neural operator models provide a discretization-invar…
On Generation in Metric Spaces
Jiaxun Li, Vinod Raman, Ambuj Tewari
We study generation in separable metric instance spaces. We extend the language generation framework from Kleinberg and Mullainathan [2024] beyond countable domains by defining nov…