AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking

Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 1 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 recall (input re-concatenated to features) to DT (ablation)Deep Thinking net · Prefix sums 512-bitpeak accuracy: 0.00 \pm 0.00 -> 96.19 \pm 3.73Improved
add recall to DT (ablation)Deep Thinking net · Mazes 59x59peak accuracy: 0.00 \pm 0.00 -> 82.72 \pm 15.14Improved
add progressive loss (alpha=0.01) to DT-Recall (ablation)DT-Recall · Mazes 59x59peak accuracy: 82.72 \pm 15.14 -> 97.30 \pm 0.68Improved
add progressive loss (alpha=1.0) to DT-Recall (ablation)DT-Recall · Prefix sums 512-bitpeak accuracy: 96.19 \pm 3.73 -> 97.12 \pm 1.88Improved
remove progressive loss from DT-Recall (ablation)DT-Recall · Chess puzzlesaverage accuracy: 83 -> 97Improved
add progressive loss (alpha=0.5) to DT-Recall (ablation)DT-Recall · Chess puzzles 600K-700Kpeak accuracy: 82.12 \pm 0.69 -> 82.69 \pm 0.27Improved
randomly sample n instead of fixing n=0 in progressive loss (ablation)DT-Recall · Prefix sums 512-bitaccuracy: 90.27 -> 97.12Improved
add recall to DT (ablation)Deep Thinking net · Chess puzzles 600K-700Kpeak accuracy: 78.81 \pm 1.04 -> 82.12 \pm 0.69Improved
add progressive loss (alpha=1.0) to DT without recall (ablation)DT · Prefix sums 512-bitpeak accuracy: 0.00 \pm 0.00 -> 11.26 \pm 6.90Improved
add progressive loss (alpha=0.01) to DT without recall (ablation)DT · Mazes 13x13peak accuracy: 85.59 \pm 2.81 -> 86.08 \pm 3.96No clear effect
add progressive loss to DT-Recall (ablation)DT-Recall · Mazes 13x13peak accuracy: 99.94 \pm 0.03 -> 99.88 \pm 0.05No clear effect
replace progressive loss with run-time weighted loss (ablation)DT-Recall · Prefix sums 512-bitaccuracy: 97.12 \pm 1.88 -> 72.45 \pm 8.91Hurt

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