Filter Results:
- Full text PDF available (49)
Publication Year
1986
2018
- This year (5)
- Last 5 years (20)
- Last 10 years (42)
Publication Type
Co-author
Journals and Conferences
Learn More
Formal languages for probabilistic modeling enable re-use, modularity, and descriptive clarity, and can foster generic inference techniques. We introduce Church, a universal language for describing… (More)
We present a new technique, failure-oblivious computing, that enables servers to execute through memory errors without memory corruption. Our safe compiler for C inserts checks that dynamically… (More)
We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statistic—informally… (More)
- Yee Whye Teh, Hal Daumé, Daniel M. Roy
- NIPS
- 2007
We introduce a new Bayesian model for hierarchical clustering based on a prior over trees called Kingman’s coalescent. We develop novel greedy and sequential Monte Carlo inferences which operate in a… (More)
A fundamental problem in the analysis of structured relational data like graphs, networks, databases, and matrices is to extract a summary of the common structure underlying relations between… (More)
One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that… (More)
- Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
- NIPS
- 2014
Ensembles of randomized decision trees, usually referred to as random forests, are widely used for classification and regression tasks in machine learning and statistics. Random forests achieve… (More)
Neural network image classifiers are known to be vulnerable to adversarial images, i.e., natural images which have been modified by an adversarial perturbation specifically designed to be… (More)
- Martin C. Rinard, Cristian Cadar, Daniel Dumitran, Daniel M. Roy, Tudor Leu
- 20th Annual Computer Security Applications…
- 2004
Buffer overflow vulnerabilities are caused by programming errors that allow an attacker to cause the program to write beyond the bounds of an allocated memory block to corrupt other data structures.… (More)
- Victor Veitch, Daniel M. Roy
- ArXiv
- 2015
We introduce a class of random graphs that we argue meets many of the desiderata one would demand of a model to serve as the foundation for a statistical analysis of real-world networks. The class of… (More)