Research map / Learning theory and algorithms / Prediction and decision losses
When Online Learning Meets ODE: Learning without Forgetting on Variable Feature Space
Diyang Li, Bin Gu
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 |
|---|---|---|---|
| Use DFLS for feature-wise online learning instead of retraining | Group Lasso · Yolanda | RMSE: 11.71 -> 11.71 | No clear effect |
| Use DFLS for feature-wise online learning instead of retraining | ℓp OLS (p = 0.5) · BNG(libras_move) | RMSE: 5.90 -> 5.90 | No clear effect |
| Use DFLS for feature-wise online learning instead of retraining | ℓp OLS (p = 4) · BNG(libras_move) | RMSE: 4.39 -> 6.39 | Mixed |
| Use DFLS for feature-wise online learning instead of retraining | Logistic Estimator · satellite_image | RMSE: 1.64 -> 1.64 | No clear effect |
| Use DFLS for feature-wise online learning instead of retraining | Poisson Regression · BNG(wisconsin) | RMSE: 32.01 -> 32.01 | No clear effect |
| Use DFLS for feature-wise online learning instead of retraining | Gamma Regression · cpu_act | RMSE: 11.95 -> 11.95 | No clear effect |
Closest papers by meaning
- Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning (NeurIPS 2024 · similarity 0.84)
- DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning (CVPR 2024 · similarity 0.84)
- One-Pass Feature Evolvable Learning with Theoretical Guarantees (ICML 2025 · similarity 0.83)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.83)
- LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning (ICLR 2025 · similarity 0.83)
- Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging (AAAI 2024 · 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.
