activity
20102025
most citedOnline Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret

88 citations · 176 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

Blockbuster, Part 1: Block-level AI Operator Fusion

Ofer Dekel

Blockbuster is a framework for AI operator fusion in inference programs. The Blockbuster framework is compatible with any multiprocessor architecture that has a tiered memory hiera…

cs.LG2018

Learning SMaLL Predictors

Vikas K. Garg, Ofer Dekel, Lin Xiao

We present a new machine learning technique for training small resource-constrained predictors. Our algorithm, the Sparse Multiprototype Linear Learner (SMaLL), is inspired by the…

cs.LG2017

Linear Learning with Sparse Data

Ofer Dekel

Linear predictors are especially useful when the data is high-dimensional and sparse. One of the standard techniques used to train a linear predictor is the Averaged Stochastic Gra…

cs.LG201556 cited

Online Learning with Feedback Graphs: Beyond Bandits

Noga Alon, Nicolò Cesa-Bianchi, Ofer Dekel +1

We study a general class of online learning problems where the feedback is specified by a graph. This class includes online prediction with expert advice and the multi-armed bandit…

cs.LG201510 cited

Bandit Convex Optimization: sqrt{T} Regret in One Dimension

Sébastien Bubeck, Ofer Dekel, Tomer Koren +1

We analyze the minimax regret of the adversarial bandit convex optimization problem. Focusing on the one-dimensional case, we prove that the minimax regret is $\widetildeΘ(\sqrt{T}…

cs.LG201288 cited

Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret

Raman Arora, Ofer Dekel, Ambuj Tewari

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn…