We propose an evolution strategies-based algorithm for estimating gradie...
Many problems in machine learning involve bilevel optimization (BLO),
in...
We propose a framework for online meta-optimization of parameters that g...
Correlations between factors of variation are prevalent in real-world da...
Unrolled computation graphs arise in many scenarios, including training ...
Ridge Rider (RR) is an algorithm for finding diverse solutions to
optimi...
We generalize gradient descent with momentum for learning in differentia...
Invertible neural networks (INNs) have been used to design generative mo...
We propose an algorithm for inexpensive gradient-based hyperparameter
op...
Hyperparameter optimization can be formulated as a bilevel optimization
...
Recurrent neural networks (RNNs) provide state-of-the-art performance in...
Bayesian neural networks (BNNs) allow us to reason about uncertainty in ...
Stochastic neural net weights are used in a variety of contexts, includi...
There is growing interest in artificial intelligence to build socially
i...