AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Linear Dynamical Systems as a Core Computational Primitive

Shiva Kaul

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 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
LDS instead of LSTM for sequential permuted MNISTLDS · Sequential permuted MNISTaccuracy (%): 92.3% -> 91.8%No clear effect
LDS instead of unfused RNN for step timeLDS · Sequential permuted MNISTstep time (ms): 324ms -> 73msImproved
LDS with 16,500 parameters instead of LSTM with 68,000LDS · Sequential permuted MNISTparameters: ~68,000 -> ~16,500Improved
LDS (linear RNN, n=160) instead of LSTM/tanh RNN/uRNN on copy memoryLDS · Copy memory T=2000parameters needed to solve: 6500 -> 3380Improved
LDStack instead of unfused RNNs for runtimeLDStack · Runtime vs sequence lengthtime (seconds)Improved
LDStack instead of CuDNN LSTM at long sequencesLDStack · Runtime vs sequence lengthtime (seconds)Mixed
simple tanh RNN on adding problemSimple RNN · Adding problemmean-squared error: 0.167Hurt
LDStack instead of LSTM on adding problemLDStack · Adding problemconvergence speedHurt

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