
A case where a spindly twolayer linear network whips any neural network with a fully connected input layer
It was conjectured that any neural network of any structure and arbitrar...
read it

Learning to Crawl
Web crawling is the problem of keeping a cache of webpages fresh, i.e., ...
read it

Adaptive scaleinvariant online algorithms for learning linear models
We consider online learning with linear models, where the algorithm pred...
read it

Bandit Principal Component Analysis
We consider a partialfeedback variant of the wellstudied online PCA pr...
read it

The Many Faces of Exponential Weights in Online Learning
A standard introduction to online learning might place Online Gradient D...
read it

Scaleinvariant unconstrained online learning
We consider a variant of online convex optimization in which both the in...
read it

Online Isotonic Regression
We consider the online version of the isotonic regression problem. Given...
read it

PCA with Gaussian perturbations
Most of machine learning deals with vector parameters. Ideally we would ...
read it

HorizonIndependent Optimal Prediction with LogLoss in Exponential Families
We study online learning under logarithmic loss with regular parametric ...
read it

Consistent Multilabel Ranking through Univariate Losses
We consider the problem of rank loss minimization in the setting of mult...
read it
Wojciech Kotłowski
is this you? claim profile