Neural Processes — mentioned by 317070

Sun, 22 Jul 2018 19:33:49 GMT

It's the opposite, they are very data efficient (compared to neural networks). Also, they are a bayesian method and give some mathematical guarantees. They are computationally expensive though. You can use them in neural nets to do few shot learning [0]. [0] https://arxiv.org/pdf/1802.07535.pdf or https://arxiv.org/abs/1807.01622

Paper and discussion history. A mention is not an endorsement.

Neural Processes — mentioned by mxwsn

Sun, 22 Jul 2018 16:13:19 GMT

I consider GPs in two ways: hyperparameter optimization (where GPs are a specific instantiation of bayesian optimization) and a powerful non-linear regression method that supports uncertainty via the rich posterior distributions you get with GPs. However, on the side of hyperparameter optimization, an experiment comparing bayesian optimization to random search with only double the computational resources [0] suggests that BO is not at least 2x better than random search which, to me, means that in practice BO isn't my first go-to for hyperparameter optimization. On the side of regression, its…

Paper and discussion history. A mention is not an endorsement.

Neural Processes · HackerPapers discussions

Neural Processes — mentioned by 317070

Neural Processes — mentioned by mxwsn