Search Results for author:
Found 4 papers, 0 papers with code
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
This framework allows us to show provable guarantees on the performance of the learned representations on the average classification task that is comprised of a subset of the same set of latent classes.
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with the ReLU activation.
Geometric Exploration for Online Control
We study the control of an \emph{unknown} linear dynamical system under general convex costs.
Learning from Censored and Dependent Data: The case of Linear Dynamics
In our analysis, we consider a "generic" Online Newton method, which uses arbitrary vectors instead of gradients, and we prove an error-bound for it.
