-
From Oluwasanmi Koyejo
Abstract: The stochastic inventory control problem under censored demands is a fundamental problem in revenue and supply chain management. A simple class of policies… -
From Oluwasanmi Koyejo
Abstract: Policy gradient methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of… -
From Oluwasanmi Koyejo
Abstract: Recent investigations into infinitely-wide deep neural networks have given rise to intriguing connections between deep networks, kernel methods, and Gaussian… -
From Oluwasanmi Koyejo
Abstract: Does deep learning actually need to be deep? In this talk, I will present some of our recent and ongoing work on Deep Equilibrium (DEQ) Models, an approach… -
From Oluwasanmi Koyejo
Abstract: We study the problem of recovering a planted matching in randomly weighted complete bipartite graphs with n nodes. For some unknown perfect matching M*, the… -
From Oluwasanmi Koyejo
Abstract: In numerous decision-making processes such as algorithm portfolio design and adaptive routing, each action incurs a random cost and yields a random and… -
From Oluwasanmi Koyejo
Abstract: Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation such as deep… -
From Oluwasanmi Koyejo
Abstract: Flexible, yet interpretable, models for the second-order temporal structure are needed in scientific analyses of high-dimensional data. We develop a… -
-
From Oluwasanmi Koyejo
Abstract: How does a 110-layer ResNet learn a high-complexity classifier using relatively few training examples and short training time? We present a theory towards… -
From Oluwasanmi Koyejo
Abstract: System identification has a long history with several well-established methods, in particular for learning linear dynamical systems from input/output data.…