
A NoFreeLunch Theorem for MultiTask Learning
Multitask learning and related areas such as multisource domain adaptat...
read it

Proper Learning, Helly Number, and an Optimal SVM Bound
The classical PAC sample complexity bounds are stated for any Empirical ...
read it

On the Value of Target Data in Transfer Learning
We aim to understand the value of additional labeled or unlabeled target...
read it

Universal Bayes consistency in metric spaces
We show that a recently proposed 1nearestneighborbased multiclass lea...
read it

VC Classes are Adversarially Robustly Learnable, but Only Improperly
We study the question of learning an adversarially robust predictor. We ...
read it

Agnostic Sample Compression for Linear Regression
We obtain the first positive results for bounded sample compression in t...
read it

Sample Compression for RealValued Learners
We give an algorithmically efficient version of the learnertocompressi...
read it

A New Lower Bound for Agnostic Learning with Sample Compression Schemes
We establish a tight characterization of the worstcase rates for the ex...
read it

Actively Avoiding Nonsense in Generative Models
A generative model may generate utter nonsense when it is fit to maximiz...
read it

Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes
This work initiates a general study of learning and generalization witho...
read it

Learning with Changing Features
In this paper we study the setting where features are added or change in...
read it

Statistical Learning under Nonstationary Mixing Processes
We study a special case of the problem of statistical learning without t...
read it

Refined Error Bounds for Several Learning Algorithms
This article studies the achievable guarantees on the error rates of cer...
read it

The Optimal Sample Complexity of PAC Learning
This work establishes a new upper bound on the number of samples suffici...
read it

Minimax Analysis of Active Learning
This work establishes distributionfree upper and lower bounds on the mi...
read it

A Compression Technique for Analyzing DisagreementBased Active Learning
We introduce a new and improved characterization of the label complexity...
read it

Surrogate Losses in Passive and Active Learning
Active learning is a type of sequential design for supervised machine le...
read it

Activized Learning: Transforming Passive to Active with Improved Label Complexity
We study the theoretical advantages of active learning over passive lear...
read it
Steve Hanneke
is this you? claim profile