Our work proves CSF can recover ground-truth features in RL, improving understanding of feature learning.
problem Understanding the role of representation and mutual information in reinforcement learning.
method Investigates Contrastive Successor Features (CSF) method for identifiable representation learning in reinforcement learning.
result Proves CSF can recover ground-truth features up to a linear transformation.
Study curve shortening flow on Riemann surfaces with conic singularities.
problem Analyzing curve shortening flow on surfaces with conic singularities.
method Generalized Huisken's comparison function to Riemann surfaces and surfaces with conic singularities. Reproofed Gage-Hamilton-Grayson theorem. Proved CSF can't touch conic singularities with cone angles ≤ π.
result CSF can't touch conic singularities with cone angles ≤ π for embedded simple closed curves.
We prove that a closed immersed plane curve with total curvature 2πm has entropy at least m times the entropy of the embedded circle, as long as it generates a type I singularity under the curve shortening flow (CSF). We construct closed immersed plane curves of total curvature 2πm whose entropy is less than m …
Paper proves conjecture about star-shaped curves evolving under GAPF, but not always preserves star shape.
problem What conditions guarantee global existence of Gage's area-preserving flow for nonconvex initial curves?
method Using Dittberner's singularity analysis theory, constructed a ``flying wing'' curve to show limitations.
result Gage's area-preserving flow does not always preserve star-shapedness of evolving curves.
Characterizes rotational solitons for curve shortening flow on revolution surfaces.
problem Understanding the behavior of curves under curve shortening flow on revolution surfaces.
method Characterization and asymptotic behavior analysis.
result Asymptotic behavior of rotational solitons to parallel geodesics.
Let M be a closed Riemannian manifold with a parallel 1-form Ω. We prove two theorems about the curve shortening flow in M. One is that the {\csf} $\ct$ in M exists for all t in [0,∞), if it satisfies Ω(T)≥0 on the initial curve $\co$. Here T is the unit tangent vector on $\co$. The other one …
We formalize AURC and develop estimators for SC systems.
problem Evaluation of SC systems' performance.
method Formal statistical formulation, Monte Carlo methods, plug-in estimators.
result Plug-in estimators are consistent, with low bias and bounded MSE.
Accurate annotation of medical image is the crucial step for image AI clinical application. However, annotating medical image will incur a great deal of annotation effort and expense due to its high complexity and needing experienced doctors. To alleviate annotation cost, some active learning methods are proposed. But …
Graph Attention Networks predict disease state from single-cell data.
problem Predicting disease state from single-cell data.
method Graph Attention Networks (GAT) for learning from both features and graph structures.
result Achieved 92% accuracy in predicting MS from single-cell data.