• Publications
  • Influence
Church: a language for generative models
TLDR
This work introduces Church, a universal language for describing stochastic generative processes, based on the Lisp model of lambda calculus, containing a pure Lisp as its deterministic subset.
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
TLDR
By optimizing the PAC-Bayes bound directly, Langford and Caruana (2001) are able to extend their approach and obtain nonvacuous generalization bounds for deep stochastic neural network classifiers with millions of parameters trained on only tens of thousands of examples.
Training generative neural networks via Maximum Mean Discrepancy optimization
TLDR
This work considers training a deep neural network to generate samples from an unknown distribution given i.i.d. data to frame learning as an optimization minimizing a two-sample test statistic, and proves bounds on the generalization error incurred by optimizing the empirical MMD.
Linear Mode Connectivity and the Lottery Ticket Hypothesis
TLDR
This work finds that standard vision models become stable to SGD noise in this way early in training, and uses this technique to study iterative magnitude pruning (IMP), the procedure used by work on the lottery ticket hypothesis to identify subnetworks that could have trained in isolation to full accuracy.
Stabilizing the Lottery Ticket Hypothesis
TLDR
This paper modifications IMP to search for subnetworks that could have been obtained by pruning early in training rather than at iteration 0, and studies subnetwork "stability," finding that - as accuracy improves in this fashion - IMP subnets train to parameters closer to those of the full network and do so with improved consistency in the face of gradient noise.
Mondrian Forests: Efficient Online Random Forests
TLDR
Mondrian forests achieve competitive predictive performance comparable with existing online random forests and periodically retrained batch random forests, while being more than an order of magnitude faster, thus representing a better computation vs accuracy tradeoff.
A study of the effect of JPG compression on adversarial images
TLDR
It is found that JPG compression often reverses the drop in classification accuracy to a large extent, but not always, and as the magnitude of the perturbations increases, JPG recompression alone is insufficient to reverse the effect.
The Mondrian Process
TLDR
A novel class of distributions, called Mondrian processes, which can be interpreted as probability distributions over kd-tree data structures, and it is shown how the process can be used as a nonparametric prior distribution in Bayesian models of relational data.
Neural Network Matrix Factorization
TLDR
This work replaces the inner product of the matrix factorization framework by a multi-layer feed-forward neural network, and learns by alternating between optimizing the network for fixed latent features, and optimizing the latent features for a fixed network.
Enhancing Server Availability and Security Through Failure-Oblivious Computing
TLDR
Failure-oblivious computing is presented, a new technique that enables servers to execute through memory errors without memory corruption and enables the servers to continue to operate successfully to service legitimate requests and satisfy the needs of their users even after attacks trigger their memory errors.
...
1
2
3
4
5
...