We present an algorithm for minimizing an objective with hard-to-compute...
The existing analysis of asynchronous stochastic gradient descent (SGD)
...
We consider potentially non-convex optimization problems, for which opti...
We propose and analyze a stochastic Newton algorithm for homogeneous
dis...
In this thesis, I study the minimax oracle complexity of distributed
sto...
We present and analyze an algorithm for optimizing smooth and convex or
...
Recent work has highlighted the role of initialization scale in determin...
We resolve the min-max complexity of distributed stochastic convex
optim...
We provide a detailed asymptotic study of gradient flow trajectories and...
We analyze Local SGD (aka parallel or federated SGD) and Minibatch SGD i...
We present a direct (primal only) derivation of Mirror Descent as a "par...
A recent line of work studies overparametrized neural networks in the "k...
We study local SGD (also known as parallel SGD and federated averaging),...
We lower bound the complexity of finding ϵ-stationary points (with
gradi...
We investigate the computational complexity of several basic linear alge...
We note that known methods achieving the optimal oracle complexity for f...
We design a general framework for answering adaptive statistical queries...
A recent line of work studies overparametrized neural networks in the
"k...
We give nearly matching upper and lower bounds on the oracle complexity ...
Classifiers can be trained with data-dependent constraints to satisfy
fa...
We suggest a general oracle-based framework that captures different para...
The problem of handling adaptivity in data analysis, intentional or not,...
We study implicit regularization when optimizing an underdetermined quad...
We provide tight upper and lower bounds on the complexity of minimizing ...