Author pages are created from data sourced from our academic publisher partnerships and public sources.
- Publications
- Influence
How to use expert advice
- N. Cesa-Bianchi, Y. Freund, D. Helmbold, D. Haussler, R. Schapire, Manfred K. Warmuth
- Mathematics, Computer Science
- STOC '93
- 1 June 1993
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 no… Expand
On-Line Portfolio Selection Using Multiplicative Updates
- D. Helmbold, R. Schapire, Y. Singer, Manfred K. Warmuth
- Computer Science, Economics
- ICML
- 1 October 1998
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 algorithm… Expand
Learning Permutations with Exponential Weights
- D. Helmbold, Manfred K. Warmuth
- Mathematics, Computer Science
- COLT
- 13 June 2007
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 the… Expand
Debugging concurrent programs
- C. McDowell, D. Helmbold
- Computer Science
- CSUR
- 1 December 1989
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 to… Expand
How to use expert advice
- N. Cesa-Bianchi, Y. Freund, D. Haussler, D. Helmbold, R. Schapire, Manfred K. Warmuth
- Computer Science
- JACM
- 1 May 1997
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 no… Expand
How to use expert advice
- N. Cesa-Bianchi, Y. Freund, D. Haussler, D. Helmbold, R. Schapire, Manfred K. Warmuth
- Mathematics, Computer Science
- JACM
- 1 May 1997
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 no… Expand
Predicting Nearly as Well as the Best Pruning of a Decision Tree
- D. Helmbold, R. Schapire
- Computer Science
- COLT
- 5 July 1995
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 reduce… Expand
Adaptive disk spin‐down for mobile computers
- D. Helmbold, D. Long, Tracey L. Sconyers, Bruce Sherrod
- Computer Science
- Mob. Networks Appl.
- 1 December 2000
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 battery… Expand
Aerial Lidar Data Classification using AdaBoost
- S. Lodha, D. Fitzpatrick, D. Helmbold
- Computer Science
- Sixth International Conference on 3-D Digital…
- 21 August 2007
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
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks
- P. Bartlett, D. Helmbold, Philip M. Long
- Computer Science, Mathematics
- Neural Computation
- 16 February 2018
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 by… Expand