AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

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

Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse

ICLR 2018 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 182 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Flipout instead of shared multiplicative Gaussian perturbationsLSTM · PTB character-level testbits-per-character: 1.230 -> 1.227Improved
Use Flipout-based DropConnect instead of shared-mask DropConnectLSTM · PTB word-level testperplexity: 75.71 -> 73.20Improved
Use Flipout instead of shared perturbationsBayes by Backprop · FC and ConvLe, mini-batch size 8192iterations to converge: about 3 times fewer iterationsImproved
Use Flipout instead of shared perturbationsBayes by Backprop · FC and ConvLe, mini-batch size 8192training speedup: 1.5x speedupImproved
Use Flipout pseudo-independent perturbations instead of fully independent perturbationsEvolution strategies · MNISTperformanceNo clear effect
Use Flipout to perturb each example pseudo-independently rather than share one perturbation across the batchWeight-perturbed neural networks · FC, ConVGG, and LSTM variance experimentsgradient varianceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy