Search Results for author:
Found 14 papers, 5 papers with code
Faster Recalibration of an Online Predictor via Approachability
Predictive models in ML need to be trustworthy and reliable, which often at the very least means outputting calibrated probabilities.
U-Calibration: Forecasting for an Unknown Agent
We show that sublinear U-calibration error is a necessary and sufficient condition for all agents to achieve sublinear regret guarantees.
Non-Stochastic CDF Estimation Using Threshold Queries
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.
Online Convex Optimization with Unbounded Memory
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.
Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem
Bandits with knapsacks (BwK) is an influential model of sequential decision-making under uncertainty that incorporates resource consumption constraints.
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case.
Direct Uncertainty Prediction for Medical Second Opinions
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.
An Alternative View: When Does SGD Escape Local Minima?
Stochastic gradient descent (SGD) is widely used in machine learning.
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
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.
Bandits and Experts in Metric Spaces
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.
Bandits with Knapsacks
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.
Dynamic Pricing with Limited Supply
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.
Multi-Armed Bandits in Metric Spaces
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.
Learning diverse rankings with multi-armed bandits
Algorithms for learning to rank Web documents usually assume a document's relevance is independent of other documents.
