activity
20162024
most citedTight Analyses for Non-Smooth Stochastic Gradient Descent

21 citations · 39 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2022★ 1 cited

Continuous Prediction with Experts' Advice

Victor Sanches Portella, Christopher Liaw, Nicholas J. A. Harvey

Prediction with experts' advice is one of the most fundamental problems in online learning and captures many of its technical challenges. A recent line of work has looked at online…

cs.LG2021★ 1 cited

Privately Learning Mixtures of Axis-Aligned Gaussians

Ishaq Aden-Ali, Hassan Ashtiani, Christopher Liaw

We consider the problem of learning mixtures of Gaussians under the constraint of approximate differential privacy. We prove that $\widetilde{O}(k^2 d \log^{3/2}(1/δ) / α^2 \vareps…

cs.LG2020

Optimal anytime regret with two experts

Nicholas J. A. Harvey, Christopher Liaw, Edwin Perkins +1

We consider the classical problem of prediction with expert advice. In the fixed-time setting, where the time horizon is known in advance, algorithms that achieve the optimal regre…

cs.LG2019

Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent

Nicholas J. A. Harvey, Christopher Liaw, Sikander Randhawa

We consider stochastic gradient descent algorithms for minimizing a non-smooth, strongly-convex function. Several forms of this algorithm, including suffix averaging, are known to…

cs.LG2018★ 21 cited

Tight Analyses for Non-Smooth Stochastic Gradient Descent

Nicholas J. A. Harvey, Christopher Liaw, Yaniv Plan +1

Consider the problem of minimizing functions that are Lipschitz and strongly convex, but not necessarily differentiable. We prove that after steps of stochastic gradient descen…

cs.LG2017

Near-optimal Sample Complexity Bounds for Robust Learning of Gaussians Mixtures via Compression Schemes

Hassan Ashtiani, Shai Ben-David, Nick Harvey +3

We prove that samples are necessary and sufficient for learning a mixture of Gaussians in , up to error in total va…