Research map / Optimization / Optimizers
Streaming Linear System Identification with Reverse Experience Replay
Suhas S Kowshik, Dheeraj Mysore Nagaraj, Prateek Jain, Praneeth Netrapalli
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Process each buffer in reverse order using SGD | Streaming LTI system identification · Synthetic VAR(1) | parameter error | Improved |
| Use standard forward-order SGD instead of reverse-order SGD | Streaming LTI system identification · Synthetic VAR(1) | parameter error | Hurt |
| Randomly sample points from each buffer instead of processing them in reverse order | Streaming LTI system identification · Synthetic VAR(1) | parameter error | Hurt |
| Use SGD with reverse experience replay | Streaming LTI system identification · VAR(A, μ) under the stated assumptions | parameter error | Improved |
| Use SGD with reverse experience replay | Streaming LTI system identification · VAR(A, μ) under the stated assumptions | prediction error | Improved |
Closest papers by meaning
- Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems (NeurIPS 2021 · similarity 0.87)
- Variance Reduction via Resampling and Experience Replay (AAAI 2026 · similarity 0.86)
- Remember and Forget for Experience Replay (ICML 2019 · similarity 0.85)
- Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms (NeurIPS 2020 · similarity 0.85)
- Gradient Descent Learns Linear Dynamical Systems (JMLR 2018 · similarity 0.85)
- ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling (NeurIPS 2026 · similarity 0.83)
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.
