Intense recent discussions have focused on how to provide individuals with control over
when their data can and cannot be used---the EU's Right To Be Forgotten regulation is an …

Abstract Domain adversarial training has been ubiquitous for achieving invariant
representations and is used widely for various domain adaptation tasks. In recent times …

We lower bound the complexity of finding ϵ-stationary points (with gradient norm at most ϵ)
using stochastic first-order methods. In a well-studied model where algorithms access …

In this paper, we propose a new technique named\textit {Stochastic Path-Integrated
Differential EstimatoR}(SPIDER), which can be used to track many deterministic quantities of …

Federated Learning (FL) is popular for communication-efficient learning from distributed
data. To utilize data at different clients without moving them to the cloud, algorithms such as …

Recent applications that arise in machine learning have surged significant interest in solving
min-max saddle point games. This problem has been extensively studied in the convex …

This paper resolves a longstanding open question pertaining to the design of near-optimal
first-order algorithms for smooth and strongly-convex-strongly-concave minimax problems …

We analyze Local SGD (aka parallel or federated SGD) and Minibatch SGD in the
heterogeneous distributed setting, where each machine has access to stochastic gradient …

While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning,
adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across …

Classical analysis of convex and non-convex optimization methods often requires the
Lipschitz continuity of the gradient, which limits the analysis to functions bounded by …