activity
20172025
most citedAlgorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks

10 citations · 43 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2025

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos +1

We study the problem of PAC learning -margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetild…

cs.LG20222 cited

Weighted Distillation with Unlabeled Examples

Fotis Iliopoulos, Vasilis Kontonis, Cenk Baykal +3

Distillation with unlabeled examples is a popular and powerful method for training deep neural networks in settings where the amount of labeled data is limited: A large ''teacher''…

cs.LG2021

Learning General Halfspaces with General Massart Noise under the Gaussian Distribution

Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2

We study the problem of PAC learning halfspaces on with Massart noise under the Gaussian distribution. In the Massart model, an adversary is allowed to flip the labe…

cs.LG20212 cited

Agnostic Proper Learning of Halfspaces under Gaussian Marginals

Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2

We study the problem of agnostically learning halfspaces under the Gaussian distribution. Our main result is the {\em first proper} learning algorithm for this problem whose sample…

cs.LG20202 cited

Convergence and Sample Complexity of SGD in GANs

Vasilis Kontonis, Sihan Liu, Christos Tzamos

We provide theoretical convergence guarantees on training Generative Adversarial Networks (GANs) via SGD. We consider learning a target distribution modeled by a 1-layer Generator…

cs.LG20209 cited

A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise

Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2

We study the problem of PAC learning homogeneous halfspaces in the presence of Tsybakov noise. In the Tsybakov noise model, the label of every sample is independently flipped with…