Statistical Learning
Distributionally Robust Optimization via Ball Oracle Acceleration
Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives.
Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise
Y et, these methods fall short of providing a complete framework for producing efficient networks.
A Multilabel Classification Framework for Approximate Nearest Neighbor Search
Approximate nearest neighbor (ANN) search is a fundamental algorithmic problem.
MNIST Partition 1 MNIST Partition 2 MNIST Partition 2 (Permuted Labels) CIFAR - 10 Equally Initialized Parameters Client Gradient Update Label Heterogeneous Domain Heterogeneous! Local Training Steps
We extensively validate our method on both label-and domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods.
Faster Linear Algebra for Distance Matrices
Such complexities are prohibitive for scaling to large datasets.
