Research map / Time series / Causal and generative time series
The Conditional Cauchy-Schwarz Divergence With Applications to Time-Series Data and Sequential Decision Making
Shujian Yu, Hongming Li, Sigurd Løkse, Robert Jenssen, José Carlos Príncipe
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 conditional CS divergence instead of conditional von Neumann on covariance | conditional divergence · Power test, sets (a) vs (b) (mean shift) | statistical power: 0.02 -> 1 | Improved |
| use conditional CS divergence instead of conditional KL | conditional divergence · Power test, sets (d) vs (e) | statistical power: 0.79 -> 0.92 | Improved |
| use conditional CS divergence instead of conditional MMD with permutation test | conditional divergence · Power test, sets (d) vs (e) | statistical power: 0 -> 0.92 | Improved |
| use conditional CS divergence instead of conditional KL | task structure discovery · Task structure (uniform input) | p(A_G != A_S): 0.293 -> 0.187 | Improved |
| use conditional CS divergence instead of conditional vN | task structure discovery · Task structure (uniform input) | p(A_G != A_S): 0.293 -> 0.187 | Improved |
| use conditional CS divergence instead of conditional vN | task structure discovery · Task structure (Gaussian input) | p(A_G != A_S): 0.062 -> 0.196 | Hurt |
| use conditional CS divergence instead of DTW on spectral clustering | time series clustering · Robot failure LP1 (spectral) | NMI: 0.0607 -> 0.686 | Improved |
| use conditional CS divergence instead of DTW on spectral clustering | time series clustering · UCLA (spectral) | NMI: 0.149 -> 0.559 | Improved |
| use conditional CS divergence instead of DTW on spectral clustering | time series clustering · ECG5000 (spectral) | NMI: 0.833 -> 0.727 | Hurt |
| use conditional CS divergence instead of DTW on k-medoids | time series clustering · Synthetic control (k-medoids) | NMI: 0.909 -> 0.745 | Hurt |
| use conditional CS divergence instead of DTW on k-medoids | time series clustering · Coffee (k-medoids) | NMI: 0.592 -> 1 | Improved |
| train with conditional CS divergence loss instead of MSE | fully-connected regressor · California housing and rotation MNIST | test RMSE | Improved |
Closest papers by meaning
- Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence (NeurIPS 2024 · similarity 0.87)
- Computing Divergences between Discrete Decomposable Models (AAAI 2023 · similarity 0.86)
- Practical and Consistent Estimation of f-Divergences (NeurIPS 2019 · similarity 0.85)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.85)
- Cauchy-Schwarz Divergence Information Bottleneck for Regression (ICLR 2024 · similarity 0.84)
- Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss (NeurIPS 2024 · 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.
