In numerous applications, the function optimized is not known a priori, but instead learned from data.

SGD that can reduce the variance and improve the complexity.

Neural Information Processing Systems http://nips.cc/

We study characteristics of receptive fields of units in deep convolutional networks.

We ask here how the brain might solve the SLAM problem.

In contrast, sampling without replacement is far less understood, yet in practice it is very common, often easier to implement, and usually performs better. In this paper, we provide competitive convergence guarantees for without-replacement sampling under several scenarios, focusing on the natural regime of few passes over the data.

RMM and DRMM enable efficient inference via message passing (e.g., using the max-sum/product

We study connections between Dykstra's algorithm for projecting onto an intersection of convex sets, the augmented Lagrangian method of multipliers or ADMM,

Recently, there are breakthroughs to compute k -SVD faster, from three distinct perspectives. The full version of this paper can be found on https://arxiv.org/abs/1607.03463 .

In recent years, automated mechanism design has emerged as one of the most practical and promising approaches to designing high-revenue combinatorial auctions.