activity
20102026
most citedLearning with a Strong Adversary

255 citations · 2.4k across the 127 of their papers we have counts for

collaborators
Showing 2016 · cs.LGShow all

5 papers · 2 filters

cs.LG2016★ 19 cited

SDP Relaxation with Randomized Rounding for Energy Disaggregation

Kiarash Shaloudegi, András György, Csaba Szepesvári +1

We develop a scalable, computationally efficient method for the task of energy disaggregation for home appliance monitoring. In this problem the goal is to estimate the energy cons…

cs.LG2016

Sequential Learning without Feedback

Manjesh Hanawal, Csaba Szepesvari, Venkatesh Saligrama

In many security and healthcare systems a sequence of features/sensors/tests are used for detection and diagnosis. Each test outputs a prediction of the latent state, and carries w…

cs.LG2016★ 5 cited

(Bandit) Convex Optimization with Biased Noisy Gradient Oracles

Xiaowei Hu, Prashanth L. A., András György +1

Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorit…

cs.LG2016★ 9 cited

Stochastic Rank-1 Bandits

Sumeet Katariya, Branislav Kveton, Csaba Szepesvari +2

We propose stochastic rank- bandits, a class of online learning problems where at each step a learning agent chooses a pair of row and column arms, and receives the product of t…

cs.LG2016★ 55 cited

DCM Bandits: Learning to Rank with Multiple Clicks

Sumeet Katariya, Branislav Kveton, Csaba Szepesvári +1

A search engine recommends to the user a list of web pages. The user examines this list, from the first page to the last, and clicks on all attractive pages until the user is satis…