We present Scaff-PD, a fast and communication-efficient algorithm for
di...
Clustering clients with similar objectives and learning a model per clus...
For a federated learning model to perform well, it is crucial to have a
...
Conformal prediction is emerging as a popular paradigm for providing rig...
The creator economy has revolutionized the way individuals can profit th...
State-of-the-art federated learning methods can perform far worse than t...
Federated learning is typically considered a beneficial technology which...
We investigate the fundamental optimization question of minimizing a tar...
Gradient-based learning algorithms have an implicit simplicity bias whic...
In this paper, we study the challenging task of Byzantine-robust
decentr...
Personalization in federated learning can improve the accuracy of a mode...
An often unquestioned assumption underlying most current federated learn...
In decentralized machine learning, workers compute model updates on thei...
Decentralized training of deep learning models is a key element for enab...
Byzantine robustness has received significant attention recently given i...
Federated learning is a challenging optimization problem due to the
hete...
Lossy gradient compression has become a practical tool to overcome the
c...
In Byzantine robust distributed optimization, a central server wants to ...
Increasingly machine learning systems are being deployed to edge servers...
While stochastic gradient descent (SGD) is still the de facto algorithm ...
Federated learning is a key scenario in modern large-scale machine learn...
We analyze (stochastic) gradient descent (SGD) with delayed updates on s...
Differential privacy is a useful tool to build machine learning models w...
We study gradient compression methods to alleviate the communication
bot...
Gradient Boosting Machine (GBM) is an extremely powerful supervised lear...
Sign-based algorithms (e.g. signSGD) have been proposed as a biased grad...
Coordinate descent with random coordinate selection is the current state...
We show that Newton's method converges globally at a linear rate for
obj...