Statistical Learning
Learning with Labeling Induced Abstentions
We assume this system has a limited budget for requesting ground-truth labels (e.g. from a
2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression
We consider distributed convex optimization problems in the regime when the communication between the server and the workers is expensive in both uplink and downlink directions.
SnapBoost: AHeterogeneousBoostingMachine
Moreover,bothframeworks are homogeneous: the hypothesis class is fixed at each boosting iteration.
ConsistencyofConstrainedSpectralClusteringunder GraphInducedFairPlantedPartitions
In this paper,we consider a setting where sensitive attributes indirectly manifest in an auxiliary representation graphrather than being directly observed.
