Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
International Conference on Learning Representations , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Cardiac Mesh Flow generates 3D+t four-chamber cardiac meshes with anatomical correspondence and volume conditioning via one-step flow matching on multi-scale deformation fields.
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
citing papers explorer
-
Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
-
Cardiac Mesh Flow: One-Step Generation of 3D+t Cardiac Four-Chamber Meshes via Flow Matching
Cardiac Mesh Flow generates 3D+t four-chamber cardiac meshes with anatomical correspondence and volume conditioning via one-step flow matching on multi-scale deformation fields.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
-
Are Candidate Models Really Needed for Active Learning?
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.