AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Differentiable Top-k with Optimal Transport

Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

NeurIPS 2020 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 26 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
add SOFT top-k beam search training to LSTM seq2seqBahdanau et al. LSTM · WMT14 En-FrBLEU: 35.38 -> 36.27Improved
use SOFT top-k gradient instead of vanilla top-k with ignored gradient in beam search training (ablation)Beam search training · WMT14 En-FrBLEU: 35.84 -> 36.27Improved
incorporate beam search into training (even with vanilla top-k) vs teacher forcing only (ablation)LSTM seq2seq · WMT14 En-FrBLEU: 35.38 -> 35.84Improved
train kNN end-to-end with SOFT top-k instead of two-stage pretrained CNN + kNNkNN classifier · CIFAR-10accuracy: 91.1% -> 92.6%Improved
SOFT top-k instead of k-times softmax relaxationkNN classifier · CIFAR-10accuracy: 92.2% -> 92.6%Improved
SOFT top-k instead of NeuralSortkNN classifier · MNISTaccuracy: 99.5% -> 99.4%No clear effect

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