2022
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference.
Huguet G, Magruder D, Tong A, Fasina O, Kuchroo M, Wolf G, Krishnaswamy S. Manifold Interpolating Optimal-Transport Flows for Trajectory Inference. Advances In Neural Information Processing Systems 2022, 35: 29705-29718. PMID: 37397786, PMCID: PMC10312391.Peer-Reviewed Original ResearchOptimal transportNeural ordinary differential equationsOrdinary differential equationsSchrödinger bridgesDifferential equationsData manifoldGeodesic distanceTrajectory inferenceDynamic modelManifold learningLatent spaceGenerative modelScRNA-seq dataPopulation snapshotsFlowEquationsManifoldSpace distanceBifurcationPopulation dynamicsGround distanceGeometryModelInferenceSpaceExploring the Geometry and Topology of Neural Network Loss Landscapes
Horoi S, Huang J, Rieck B, Lajoie G, Wolf G, Krishnaswamy S. Exploring the Geometry and Topology of Neural Network Loss Landscapes. Lecture Notes In Computer Science 2022, 13205: 171-184. DOI: 10.1007/978-3-031-01333-1_14.Peer-Reviewed Original ResearchLoss landscapeNon-linear dimensionality reductionLandscape geometryGeneralization performanceLocal minimaDimensionality reduction techniquesLinear natureReduction techniquesDimensionality reductionGeometrySuch visualization methodsCaptures featuresJumpNetwork's abilityNeural networkTrajectoriesRecent workTopologyNetwork
2019
Compressed Diffusion
Gigante S, Stanley J, Vu N, van Dijk D, Moon K, Wolf G, Krishnaswamy S. Compressed Diffusion. 2019, 00: 1-4. DOI: 10.1109/sampta45681.2019.9030994.Peer-Reviewed Original ResearchData regionsModern data analysisDiffusion mapsMost kernel methodsDiffusion geometryHeavy computational loadData pointsRelated embeddingsKernel-based methodsCubic complexityDiffusion map embeddingBig datasetsCorrelation kernelLower dimensionSpectral embeddingComputational loadKernel methodDiffusion relationManifold learningLocal geometryDiffusion processEmbeddingTheoretical connectionsGeometryIntrinsic structure