SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.04386 · 2018

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
IntelLabs/bayesian-torch extension 1 of 1
copy not recorded — 0 of 1
FunctionStatusWhere it lives
validate Ran IntelLabs/bayesian-torch/bayesian_torch/examples/main_bayesian_flipout_cifar.py
code served (permissive licence) · get_code("befe4ccdb8a4244e")
accuracy Not yet run this paper's copy was not recorded; identical code first harvested from snu-mllab/PuzzleMix
pointer only · get_code("f0c9a29156911331")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the examples in a mini-batch typically share the same weight perturbation, thereby limiting the variance reduction effect of large mini-batches. We introduce flipout, an efficient method for decorrelating the gradients within a mini-batch by implicitly sampling pseudo-independent weight perturbations for each example. Empirically, flipout achieves the ideal linear variance reduction for fully connected networks, convolutional networks, and RNNs. We find significant speedups in training neural networks with multiplicative Gaussian perturbations. We show that flipout is effective at regularizing LSTMs, and outperforms previous methods. Flipout also enables us to vectorize evolution strategies: in our experiments, a single GPU with flipout can handle the same throughput as at least 40 CPU cores using existing methods, equivalent to a factor-of-4 cost reduction on Amazon Web Services.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1803.04386")
get_code_for_paper("1803.04386")
have("1803.04386")

Connect an agent — have() is free.