no code implementations • 25 Oct 2023 • Princewill Okoroafor, Robert Kleinberg, Wen Sun
Predictive models in ML need to be trustworthy and reliable, which often at the very least means outputting calibrated probabilities.
no code implementations • 30 Jun 2023 • Robert Kleinberg, Renato Paes Leme, Jon Schneider, Yifeng Teng
We show that sublinear U-calibration error is a necessary and sufficient condition for all agents to achieve sublinear regret guarantees.
no code implementations • 13 Jan 2023 • Princewill Okoroafor, Vaishnavi Gupta, Robert Kleinberg, Eleanor Goh
Along the way to designing our algorithm, we consider a more general model in which the algorithm is allowed to make a limited number of simultaneous threshold queries on each sample.
1 code implementation • NeurIPS 2023 • Raunak Kumar, Sarah Dean, Robert Kleinberg
As a special case, we prove the first non-trivial lower bound for OCO with finite memory \citep{anavaHM2015online}, which could be of independent interest, and also improve existing upper bounds.
1 code implementation • 24 Sep 2022 • Raunak Kumar, Robert Kleinberg
Bandits with knapsacks (BwK) is an influential model of sequential decision-making under uncertainty that incorporates resource consumption constraints.
1 code implementation • NeurIPS 2019 • Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, Devon Graham
Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case.
no code implementations • 4 Jul 2018 • Maithra Raghu, Katy Blumer, Rory Sayres, Ziad Obermeyer, Robert Kleinberg, Sendhil Mullainathan, Jon Kleinberg
Our central methodological finding is that Direct Uncertainty Prediction (DUP), training a model to predict an uncertainty score directly from the raw patient features, works better than Uncertainty Via Classification, the two-step process of training a classifier and postprocessing the output distribution to give an uncertainty score.
no code implementations • ICML 2018 • Robert Kleinberg, Yuanzhi Li, Yang Yuan
Stochastic gradient descent (SGD) is widely used in machine learning.
1 code implementation • ICML 2018 • Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon Kleinberg
Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization.
no code implementations • 4 Dec 2013 • Robert Kleinberg, Aleksandrs Slivkins, Eli Upfal
In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric.
no code implementations • 11 May 2013 • Ashwinkumar Badanidiyuru, Robert Kleinberg, Aleksandrs Slivkins
As one example of a concrete application, we consider the problem of dynamic posted pricing with limited supply and obtain the first algorithm whose regret, with respect to the optimal dynamic policy, is sublinear in the supply.
no code implementations • 20 Aug 2011 • Moshe Babaioff, Shaddin Dughmi, Robert Kleinberg, Aleksandrs Slivkins
The performance guarantee for the same mechanism can be improved to $O(\sqrt{k} \log n)$, with a distribution-dependent constant, if $k/n$ is sufficiently small.
2 code implementations • 29 Sep 2008 • Robert Kleinberg, Aleksandrs Slivkins, Eli Upfal
In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric.
no code implementations • International Conference on Machine Learning 2008 • Filip Radlinski, Robert Kleinberg, Thorsten Joachims
Algorithms for learning to rank Web documents usually assume a document's relevance is independent of other documents.