2 citations · 3 across the 8 of their papers we have counts for
10 papers
A regret minimization approach to fixed-point iterations
Joon Kwon
We propose a conversion scheme that turns regret minimizing algorithms into fixed point iterations, with convergence guarantees following from regret bounds. The resulting iteratio…
Finite-sum optimization: Adaptivity to smoothness and loopless variance reduction
Bastien Batardière, Joon Kwon
For finite-sum optimization, variance-reduced gradient methods (VR) compute at each iteration the gradient of a single function (or of a mini-batch), and yet achieve faster converg…
Time-Dependent Blackwell Approachability and Application to Absorbing Games
Joon Kwon, Yijun Wan, Bruno Ziliotto
Blackwell's approachability (Blackwell, 1954, 1956) is a very general online learning framework where a Decision Maker obtains vector-valued outcomes, and aims at the convergence o…
Refined approachability algorithms and application to regret minimization with global costs
Joon Kwon
Blackwell's approachability is a framework where two players, the Decision Maker and the Environment, play a repeated game with vector-valued payoffs. The goal of the Decision Make…
Unifying mirror descent and dual averaging
Anatoli Juditsky, Joon Kwon, Éric Moulines
We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this fami…
A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning
Joon Kwon, Guillaume Lecué, Matthieu Lerasle
Hyperparameters tuning and model selection are important steps in machine learning. Unfortunately, classical hyperparameter calibration and model selection procedures are sensitive…
Sparse Stochastic Bandits
Joon Kwon, Vianney Perchet, Claire Vernade
In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward. Guarantees can be ob…
Gains and Losses are Fundamentally Different in Regret Minimization: The Sparse Case
Joon Kwon, Vianney Perchet
We demonstrate that, in the classical non-stochastic regret minimization problem with decisions, gains and losses to be respectively maximized or minimized are fundamentally di…
A continuous-time approach to online optimization
Joon Kwon, Panayotis Mertikopoulos
We consider a family of learning strategies for online optimization problems that evolve in continuous time and we show that they lead to no regret. From a more traditional, discre…
A universal bound on the variations of bounded convex functions
Joon Kwon
Given a convex set in a real vector space and two points , we investivate which are the possible values for the variation , where $f:C\longrightarrow […