30 citations · 102 across the 35 of their papers we have counts for
6 papers · 1 filter
Differentially Private Online-to-Batch for Smooth Losses
Qinzi Zhang, Hoang Tran, Ashok Cutkosky
We develop a new reduction that converts any online convex optimization algorithm suffering regret into an -differentially private stochastic convex optimization a…
Momentum Aggregation for Private Non-convex ERM
Hoang Tran, Ashok Cutkosky
We introduce new algorithms and convergence guarantees for privacy-preserving non-convex Empirical Risk Minimization (ERM) on smooth -dimensional objectives. We develop an impro…
Parameter-free Regret in High Probability with Heavy Tails
Jiujia Zhang, Ashok Cutkosky
We present new algorithms for online convex optimization over unbounded domains that obtain parameter-free regret in high-probability given access only to potentially heavy-tailed…
Optimal Comparator Adaptive Online Learning with Switching Cost
Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
Practical online learning tasks are often naturally defined on unconstrained domains, where optimal algorithms for general convex losses are characterized by the notion of comparat…
Parameter-free Mirror Descent
Andrew Jacobsen, Ashok Cutkosky
We develop a modified online mirror descent framework that is suitable for building adaptive and parameter-free algorithms in unbounded domains. We leverage this technique to devel…
PDE-Based Optimal Strategy for Unconstrained Online Learning
Zhiyu Zhang, Ashok Cutkosky, Ioannis Paschalidis
Unconstrained Online Linear Optimization (OLO) is a practical problem setting to study the training of machine learning models. Existing works proposed a number of potential-based…