hi gang,
This week we have two practice talks (well one practice talk and one practice poster :-)) for the upcoming NIPS conference. Guillaume and Arnaud will each have about 30 minutes to give us there best pitch. Come with questions, comments and critiques.
When: Firday Dec. 2nd, 14h00 Where: TBA
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Speaker: Guillaume Desjardins Title: On Tracking The Partition Function
Markov Random Fields (MRFs) have proven very powerful both as density estimators and feature extractors for classification. However, their use is often limited by an inability to estimate the partition function $Z$. In this paper, we exploit the gradient descent training procedure of restricted Boltzmann machines (a type of MRF) to {\bf track} the log partition function during learning. Our method relies on two distinct sources of information: (1) estimating the change $\Delta Z$ incurred by each gradient update, (2) estimating the difference in $Z$ over a small set of tempered distributions using bridge sampling. The two sources of information are then combined using an inference procedure similar to Kalman filtering. Learning MRFs through Tempered Stochastic Maximum Likelihood, we can estimate $Z$ using no more temperatures than are required for learning. Comparing to both exact values and estimates using annealed importance sampling (AIS), we show on several datasets that our method is able to accurately track the log partition function. In contrast to AIS, our method provides this estimate at each time-step, at a computational cost similar to that required for training alone.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Speaker: Arnaud Bergeron A Common GPU n-Dimensional Array for Python and C
Currently there are multiple incompatible array/matrix/n-dimensional base object implementations for GPUs. This hinders the sharing of GPU code and causes duplicate development work. This paper proposes and presents a first version of a common GPU n-dimensional array (tensor) named GpuNdArray that works with both CUDA and OpenCL. It will be usable from Python, C, and possibly other programming languages.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Cheers, Aaron
Afficher les réponses par date