The discrepancy of the n × n greater-than matrix is shown to be
π/2 ln n...
We provide a unified framework for characterizing pure and approximate
d...
Replicability is essential in science as it allows us to validate and ve...
A seminal result in learning theory characterizes the PAC learnability o...
We study the implicit bias of ReLU neural networks trained by a variant ...
We give tight bounds on the degree ℓ homogenous parts f_ℓ of a
bounded f...
Essential covers were introduced by Linial and Radhakrishnan as a model ...
Key-agreement protocols whose security is proven in the random oracle mo...
We prove that at least Ω(n^0.51) hyperplanes are needed to slice all
edg...
How quickly can a given class of concepts be learned from examples? It i...
This work provides an additional step in the theoretical understanding o...
How many bits of information are revealed by a learning algorithm for a
...
We study and provide exposition to several phenomena that are related to...
We consider Evolution Strategies operating only with isotropic Gaussian
...
How many bits of information are required to PAC learn a class of hypoth...
This work introduces a model of distributed learning in the spirit of Ya...
We study learning algorithms that are restricted to revealing little
inf...
We show that the Radon number characterizes the existence of weak nets i...
We study the theoretical capacity to statistically learn local landscape...