
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games
Which classes can be learned properly in the online model? – that is, by...
read it

SGD Generalizes Better Than GD (And Regularization Doesn't Help)
We give a new separation result between the generalization performance o...
read it

A Limitation of the PACBayes Framework
PACBayes is a useful framework for deriving generalization bounds which...
read it

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
The notion of implicit bias, or implicit regularization, has been sugges...
read it

An Equivalence Between Private Classification and Online Prediction
We prove that every concept class with finite Littlestone dimension can ...
read it

Prediction with Corrupted Expert Advice
We revisit the fundamental problem of prediction with expert advice, in ...
read it

Graphbased Discriminators: Sample Complexity and Expressiveness
A basic question in learning theory is to identify if two distributions ...
read it

On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes
We study the expressive power of kernel methods and the algorithmic feas...
read it

Passing Tests without Memorizing: Two Models for Fooling Discriminators
We introduce two mathematical frameworks for foolability in the context ...
read it

Private PAC learning implies finite Littlestone dimension
We show that every approximately differentially private learning algorit...
read it

On Communication Complexity of Classification Problems
This work introduces a model of distributed learning in the spirit of Ya...
read it

On the Computational Efficiency of Training Neural Networks
It is wellknown that neural networks are computationally hard to train....
read it

An Algorithm for Training Polynomial Networks
We consider deep neural networks, in which the output of each node is a ...
read it
Roi Livni
is this you? claim profile