Beyond Adversarial Training: A Robust Counterpart Approach to HSVM
18 Jan 2026
The Robust HSVM manages data uncertainty structures using robust counterpart formulations and SDP relaxation for stable non-convex optimization.
HSVM Decision Boundaries: Visualizing PGD vs. SDP and Moment Relaxation
17 Jan 2026
Moment-SOS relaxation outperforms PGD in HSVM benchmarks, providing robust decision boundaries and smaller optimality gaps across complex datasets.
Platt Scaling for HSVM: Calibrating Binary to Probabilistic Predictions
16 Jan 2026
Platt scaling calibrates HSVM binary predictions into probabilities using logistic regression, enabling effective multiclass classification
Dual Cones & Quadratic Modules: The Geometry of Global Optimality
16 Jan 2026
Learn how sparse POP and semidefinite relaxations find global optima for NP-hard problems.
Extracting Solutions from SDP Relaxations via Rank-One Approximation
15 Jan 2026
Learn how to extract high-quality solutions from SDP relaxations using scaled eigendirections, Gaussian randomizations, and matrix column scaling
Mapping Lorentz Decision Boundaries to the Poincaré Ball
15 Jan 2026
Learn how to transform soft-margin constraints into polynomial form using Taylor expansion and map Lorentz manifold lines to Poincaré ball arcs.
Future Directions in Hyperbolic SVM and Geometric Machine Learning
15 Jan 2026
Explore the advantages and limitations of SDP and Moment-SOS relaxations for Hyperbolic SVM.
Comparing One-vs-Rest and One-vs-One Training in Hyperbolic SVM
15 Jan 2026
Compare One-vs-Rest and One-vs-One training schemes for stability, scalability, and classification accuracy.
Optimization Performance on Synthetic Gaussian and Tree Embeddings
14 Jan 2026
Analyze the performance of SDP and Moment-SOS relaxations on synthetic hyperbolic datasets.