204 citations · 213 across the 4 of their papers we have counts for
4 papers · 1 filter
Learning from Censored and Dependent Data: The case of Linear Dynamics
Orestis Plevrakis
Observations from dynamical systems often exhibit irregularities, such as censoring, where values are recorded only if they fall within a certain range. Censoring is ubiquitous in…
Geometric Exploration for Online Control
Orestis Plevrakis, Elad Hazan
We study the control of an \emph{unknown} linear dynamical system under general convex costs. The objective is minimizing regret vs. the class of disturbance-feedback-controllers,…
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Yi Zhang, Orestis Plevrakis, Simon S. Du +3
Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. Howev…
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak +2
Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods a…