1 citations · 2 across the 7 of their papers we have counts for
7 papers
On the Differential-Geometric Equivalence of Hellinger-Kantorovich and Cone-Wasserstein Spaces
Tristan Luca Saidi, Gonzalo Mena, Florian Gunsilius
The Hellinger-Kantorovich (HK) space provides a natural geometry for nonnegative measures with varying total mass, but its differential-geometric structure is less well understood…
Wasserstein Parallel Transport for Predicting the Dynamics of Statistical Systems
Tristan Luca Saidi, Gonzalo Mena, Larry Wasserman +1
Many scientific systems, such as cellular populations or economic cohorts, are naturally described by probability distributions that evolve over time. Predicting how such a system…
EmbedOR: Provable Cluster-Preserving Visualizations with Curvature-Based Stochastic Neighbor Embeddings
Tristan Luca Saidi, Abigail Hickok, Bastian Rieck +1
Stochastic Neighbor Embedding (SNE) algorithms like UMAP and tSNE often produce visualizations that do not preserve the geometry of noisy and high dimensional data. In particular,…
Recovering Manifold Structure Using Ollivier-Ricci Curvature
Tristan Luca Saidi, Abigail Hickok, Andrew J. Blumberg
We introduce ORC-ManL, a new algorithm to prune spurious edges from nearest neighbor graphs using a criterion based on Ollivier-Ricci curvature and estimated metric distortion. Our…
Ab Initio Structure Solutions from Nanocrystalline Powder Diffraction Data
Gabe Guo, Tristan Saidi, Maxwell Terban +3
A major challenge in materials science is the determination of the structure of nanometer sized objects. Here we present a novel approach that uses a generative machine learning mo…
RR: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training
Gagan Khandate, Tristan L. Saidi, Siqi Shang +5
We present a method for enabling Reinforcement Learning of motor control policies for complex skills such as dexterous manipulation. We posit that a key difficulty for training suc…