AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

Suhas S Kowshik, Dheeraj Mysore Nagaraj, Prateek Jain, Praneeth Netrapalli

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of MDPs · 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
Use Quasi Newton updates normalized by the empirical second-moment matrix instead of mixing-time-based subsamplingOffline NLDS parameter estimation · Non-mixing NLDSsquared Frobenius parameter error: \frac{d^2\tmix}{T} -> \frac{d^2\sigma^2}{T\lmin{\hat{G}}}Improved
Use Quasi Newton updates for offline estimation under finite fourth-moment noiseOffline NLDS parameter estimation · Mixing NLDSsquared Frobenius parameter error: \frac{d^2\tmix}{T} -> \frac{d^2\sigma^2}{T\lmin{G}}Improved
Process samples in reverse order within buffers, with gaps between buffersSGD-RER · Synthetic leaky-ReLU NLDSFrobenius parameter errorImproved
Use SGD-RER instead of forward SGD or random experience replayStreaming NLDS estimation · Synthetic leaky-ReLU NLDSFrobenius parameter errorImproved
Increase the SGD-RER buffer size beyond the tested robust range (ablation)SGD-RER · Synthetic NLDS, buffer-size experimentFrobenius parameter errorHurt
Use a non-expansive ReLU link for parameter recoveryNLDS parameter estimation · ReLU NLDSminimax loss: c_0\min\left(1,\frac{\exp(c_1d)}{T}\right)Hurt
Use GLMtron rather than Quasi Newton updatesOffline NLDS estimation · Synthetic leaky-ReLU NLDSconvergence timeHurt
Use SGD-RER with heavy-tailed Student t noiseSGD-RER · Synthetic NLDS with Student t noise, scale ν = 4.1Frobenius parameter errorNo 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