Probabilistic ML: Natural Gradients and Statistical Manifolds Explained
21 Jan 2026
Explore the role of Fisher information, KL divergence, and natural gradients in optimizing probability distributions for Deep Learning.
Deep Learning via Continuous-Time Systems: Neural ODEs and Normalizing Flows Explained
21 Jan 2026
Learn how Neural ODEs and Normalizing Flows revolutionize Deep Learning by framing machine learning tasks as continuous-time optimal control problems.
Four Key Trends in Theoretical Machine Learning (2026)
21 Jan 2026
Explore the four research pillars reshaping theoretical ML: control theory, probabilistic modeling, geometric ML, and physics-informed algorithms.
Geometric Deep Learning: Swarming Dynamics on Lie Groups and Spheres
21 Jan 2026
Kuramoto models and swarming dynamics offer a powerful framework for Machine Learning over non-Euclidean data, Lie groups, and manifolds.
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