123 citations · 1.5k across the 106 of their papers we have counts for
126 papers
Wasserstein Distributionally Robust Regret-Optimal Control under Partial Observability
Joudi Hajar, Taylan Kargin, Babak Hassibi
This paper presents a framework for Wasserstein distributionally robust (DR) regret-optimal (RO) control in the context of partially observable systems. DR-RO control considers the…
The Generalization Error of Stochastic Mirror Descent on Over-Parametrized Linear Models
Danil Akhtiamov, Babak Hassibi
Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understo…
Precise Asymptotic Analysis of Deep Random Feature Models
David Bosch, Ashkan Panahi, Babak Hassibi
We provide exact asymptotic expressions for the performance of regression by an layer deep random feature (RF) model, where the input is mapped through multiple random embeddin…
Stochastic Mirror Descent in Average Ensemble Models
Taylan Kargin, Fariborz Salehi, Babak Hassibi
The stochastic mirror descent (SMD) algorithm is a general class of training algorithms, which includes the celebrated stochastic gradient descent (SGD), as a special case. It util…
Thompson Sampling Achieves Regret in Linear Quadratic Control
Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli +2
Thompson Sampling (TS) is an efficient method for decision-making under uncertainty, where an action is sampled from a carefully prescribed distribution which is updated based on t…
Explicit Regularization via Regularizer Mirror Descent
Navid Azizan, Sahin Lale, Babak Hassibi
Despite perfectly interpolating the training data, deep neural networks (DNNs) can often generalize fairly well, in part due to the "implicit regularization" induced by the learnin…