AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Towards Hardware-Aware Tractable Learning of Probabilistic Models

Laura I Galindez Olascoaga, Wannes Meert, Nimish Shah, Marian Verhelst, Guy Van den Broeck

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems

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
scale precision down from 64-bit and prune features/sensors jointly (ablation)hardware-aware PSDD/AC optimization · HAR, AC evaluation costcomputational costImproved
tolerate larger accuracy loss when choosing Pareto configuration (ablation)hardware-aware PSDD/AC optimization · HAR, AC evaluation costcomputational cost: up to 3 orders of magnitudeImproved
prune features with AC simplification (Algorithm 2) (ablation)hardware-aware PSDD/AC optimization · HARcomputational cost per feature pruned: 2 to 10 %Improved
prune 11 of 28 features (ablation)hardware-aware PSDD/AC optimization · HAR traincomputational cost: 53%Improved
use smaller model alpha3, prune 18 features, one sensor off, 32 bit, with 0.4% accuracy loss (ablation)hardware-aware PSDD/AC optimization · HAR traincost: 13%Improved
evaluate Pareto configs on test data rather than trainhardware-aware PSDD/AC optimization · HARaccuracy: within +-1%No clear effect
random failure of feature sets (|F|/10, |F|/5, |F|/2)hardware-aware PSDD/AC optimization · HAR Pareto configsaccuracy: -2%Hurt
compare against TAN classifierhardware-aware PSDD/AC optimization · HARcost and accuracyImproved
switch operating points at run-time with activity-based policyhardware-aware PSDD/AC optimization · HAR testcost-accuracy trade-offImproved
choose operating pt. 2 versus operating pt. 1 (full model) (ablation)hardware-aware PSDD/AC optimization · WiltC_AC: 1 -> 0.07Improved
choose operating pt. 4 versus operating pt. 1 (ablation)hardware-aware PSDD/AC optimization · Banknotetest accuracy: 95.6 -> 86.8Hurt
choose operating pt. 4 versus operating pt. 1 (ablation)hardware-aware PSDD/AC optimization · Wilttest accuracy: 97.5 -> 97.5No 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