19 citations · 27 across the 8 of their papers we have counts for
8 papers
Mirror Polyak and a Primal-Dual Lifting
Frederik Kunstner, Ryan D'Orazio, Victor S. Portella +1
First-order methods typically require a specific step-size that depends on the regularity conditions of the objective function, such as the smoothness, Lipschitz continuity, or str…
A second order regret bound for NormalHedge
Yoav Freund, Nicholas J. A. Harvey, Victor S. Portella +2
We consider the problem of prediction with expert advice for ``easy'' sequences. We show that a variant of NormalHedge enjoys a second-order -quantile regret bound of $O\big(\sq…
Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes
Victor S. Portella, Nick Harvey
We prove lower bounds on the number of samples needed to privately estimate the covariance matrix of a Gaussian distribution. Our bounds match existing upper bounds in the widest k…
Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
Frederik Kunstner, Victor S. Portella, Mark Schmidt +1
The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically opti…
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…
Efficient and Optimal Fixed-Time Regret with Two Experts
Laura Greenstreet, Nicholas J. A. Harvey, Victor Sanches Portella
Prediction with expert advice is a foundational problem in online learning. In instances with rounds and experts, the classical Multiplicative Weights Update method suffers…
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
Yihan Zhou, Victor S. Portella, Mark Schmidt +1
In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret. Moreover, many algorithms have only logarithmic…
Online mirror descent and dual averaging: keeping pace in the dynamic case
Huang Fang, Nicholas J. A. Harvey, Victor S. Portella +1
Online mirror descent (OMD) and dual averaging (DA) -- two fundamental algorithms for online convex optimization -- are known to have very similar (and sometimes identical) perform…