most citedBetter Mini-Batch Algorithms via Accelerated Gradient Methods

150 citations · 359 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG201371 cited

Online Learning for Time Series Prediction

Oren Anava, Elad Hazan, Shie Mannor +1

In this paper we address the problem of predicting a time series using the ARMA (autoregressive moving average) model, under minimal assumptions on the noise terms. Using regret mi…

cs.LG2012411 cited

Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes

Ohad Shamir, Tong Zhang

Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classica…

cs.LG201287 cited

On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization

Ohad Shamir

The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much a…

cs.LG201210 cited

Decoupling Exploration and Exploitation in Multi-Armed Bandits

Orly Avner, Shie Mannor, Ohad Shamir

We consider a multi-armed bandit problem where the decision maker can explore and exploit different arms at every round. The exploited arm adds to the decision maker's cumulative r…

cs.LG2011150 cited

Better Mini-Batch Algorithms via Accelerated Gradient Methods

Andrew Cotter, Ohad Shamir, Nathan Srebro +1

Mini-batch algorithms have been proposed as a way to speed-up stochastic convex optimization problems. We study how such algorithms can be improved using accelerated gradient metho…

cs.LG201138 cited

Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions

Rina Foygel, Ruslan Salakhutdinov, Ohad Shamir +1

We provide rigorous guarantees on learning with the weighted trace-norm under arbitrary sampling distributions. We show that the standard weighted trace-norm might fail when the sa…