Research map / Optimization / Nonconvex and smooth optimization
Projective Quadratic Regression for Online Learning
Wenye Ma
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 PQR (k=2000) instead of the strongest listed baseline | Online rating prediction · ML100K, ML1M, and ML10M | RMSE: 1.0312 -> 1.0215; 1.0403 -> 1.0190; 0.9572 -> 0.9536 | Improved |
| Use PQR (k=8000) instead of FM | Online binary classification · Avazu | AUC: 0.7752 -> 0.7785 | Improved |
| Use PQR (k=8000) instead of FM | Online binary classification · Avazu | LogLoss: 0.3840 -> 0.3812 | Improved |
| Use PQR (k=2000) instead of LR | Online binary classification · Avazu | Training Time: 1× -> 3.3× | Hurt |
| Use PQR (k=2000) instead of LR | Online binary classification · Avazu | Model Size: 16.37K -> 0.68M | Hurt |
| Use PQR (k=1000) instead of FM | Online binary classification · Criteo | AUC: 0.7218 -> 0.7221 | Improved |
| Use PQR (k=1000) instead of FM | Online binary classification · Criteo | LogLoss: 0.5068 -> 0.5066 | Improved |
| Use PQR (k=200) instead of LR | Online binary classification · Criteo | Training Time: 1× -> 17.1× | Hurt |
| Use PQR (k=200) instead of LR | Online binary classification · Criteo | Model Size: 1.09K -> 18.30K | Hurt |
| Use PQR (k=100) instead of FM | Online binary classification · KDD2012 | AUC: 0.7968 -> 0.8016 | Improved |
| Use PQR (k=100) instead of DiFacto | Online binary classification · KDD2012 | LogLoss: 0.1534 -> 0.1523 | Improved |
| Use PQR (k=20) instead of LR | Online binary classification · KDD2012 | Training Time: 1× -> 3.1× | Hurt |
Closest papers by meaning
- Online Convex Optimization in the Random Order Model (ICML 2020 · similarity 0.84)
- Online Learning Under a Separable Stochastic Approximation Framework (TPAMI 2024 · similarity 0.84)
- Adaptive Scale-Invariant Online Algorithms for Learning Linear Models (ICML 2019 · similarity 0.84)
- Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP (ICML 2017 · similarity 0.84)
- Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach (NeurIPS 2023 · similarity 0.84)
- Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent (ICML 2025 · similarity 0.84)
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.
