• Publications
  • Influence
How to use expert advice
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called `experts''. Our analysis is for worst-case situations, i.e., we make noExpand
  • 607
  • 44
  • PDF
On-Line Portfolio Selection Using Multiplicative Updates
We present an on-line investment algorithm that achieves almost the same wealth as the best constant-rebalanced portfolio determined in hindsight from the actual market outcomes. The algorithmExpand
  • 279
  • 36
  • PDF
Learning Permutations with Exponential Weights
We give an algorithm for learning a permutation on-line. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic matrix. This matrix is updated by multiplying theExpand
  • 110
  • 18
  • PDF
Debugging concurrent programs
The main problems associated with debugging concurrent programs are increased complexity, the "probe effect," nonrepeatability, and the lack of a synchronized global clock. The probe effect refers toExpand
  • 452
  • 17
  • PDF
How to use expert advice
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called experts. Our analysis is for worst-case situations, i.e., we make noExpand
  • 209
  • 14
How to use expert advice
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called experts. Our analysis is for worst-case situations, i.e., we make noExpand
  • 210
  • 14
Predicting Nearly as Well as the Best Pruning of a Decision Tree
Many algorithms for inferring a decision tree from data involve a two-phase process: First, a very large decision tree is grown which typically ends up “over-fitting” the data. To reduceExpand
  • 101
  • 14
Adaptive disk spin‐down for mobile computers
We address the problem of deciding when to spin down the disk of a mobile computer in order to extend battery life. One of the most critical resources in mobile computing environments is batteryExpand
  • 137
  • 10
  • PDF
Aerial Lidar Data Classification using AdaBoost
We use the AdaBoost algorithm to classify 3D aerial lidar scattered height data into four categories: road, grass, buildings, and trees. To do so we use five features: height, height variation,Expand
  • 94
  • 10
  • PDF
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks
We analyze algorithms for approximating a function f(x)=Φx mapping ℜd to ℜd using deep linear neural networks, that is, that learn a function h parameterized by matrices Θ1,…,ΘL and defined byExpand
  • 58
  • 10
  • PDF