We propose a fast approximation method of a softmax function with a very large vocabulary using singular value decomposition (SVD).

Echolocation problem can be sub-divided into estimating range, height and azimuth angle of objects in the environment.

The proposed algorithm features probabilistic interpretation, efficient updating rules and flexible modulation on whether learners focus on their specific task or on jointly address all tasks.

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

The exponential mechanism is a general method to construct a randomized estimator that satisfies ( ε, 0) -differential privacy. Recently, Wang et al. showed that the Gibbs posterior, which is a data-dependent probability distribution that contains the Bayesian posterior, is essentially equivalent to the exponential mechanism under certain boundedness conditions on the loss function. While the exponential mechanism provides a way to build an (ε, 0) -differential private algorithm, it requires boundedness of the loss function, which is quite stringent for some learning problems. In this paper, we focus on (ε,δ) -differential privacy of Gibbs posteriors with convex and Lipschitz loss functions. Our result extends the classical exponential mechanism, allowing the loss functions to have an unbounded sensitivity.

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

Such a model is known as sparse multiple index model (MIM).

One important problem is the large memory consumption required by the BPTT.

Research on word embeddings has drawn significant interest in machine learning and natural language processing.

The marginal likelihood, or model evidence, is a key quantity in Bayesian parameter estimation and model comparison.