Statistical Learning
CANIT A: Faster Rates for Distributed Convex Optimization with Communication Compression
Due to the high communication cost in distributed and federated learning, methods relying on compressed communication are becoming increasingly popular.
T orsional Geometric Generation of Molecular 3D Conformer Ensembles
Prediction of a molecule's 3D conformer ensemble from the molecular graph holds
Contrastive learning of global and local features for medical image segmentation with limited annotations
For Prostate, although we have 48 volumes, labels were provided only for a subset of them, so the number of volumes for each set were adjusted accordingly. We used the ACDC dataset for these experiments. Here, we studied the effect of the batch size used during the encoder pre-training. The results are presented in Table 2. We observed that for medical images, higher batch sizes do not improve the results any further, rather the performance deteriorated for the batch size of 450.
On Convergence of Nearest Neighbor Classifiers over Feature Transformations
In this paper, we take a first step towards bridging this gap. We provide a novel analysis on the convergence rates of a kNN classifier over transformed features.