We develop a principled approach to end-to-end learning in stochastic
op...
We propose a policy gradient algorithm for robust infinite-horizon Marko...
This paper proposes a statistically optimal approach for learning a func...
We present ISAAC (Input-baSed ApproximAte Curvature), a novel method tha...
Counterexample-guided repair aims at creating neural networks with
mathe...
We study a stochastic program where the probability distribution of the
...
Training models that perform well under distribution shifts is a central...
We propose a principled method for projecting an arbitrary square matrix...
We present a quantum algorithm to compute the discrete Legendre-Fenchel
...
The main theme of this thesis is the development of computational method...