Search Results for author:
Found 8 papers, 2 papers with code
When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making
Surprisingly, we show that for multiple of noise models, it is optimal to set $k \in [2, n-1]$ - that is, there are strict benefits to collaborating, even when the human and algorithm have equal accuracy separately.
Congested Bandits: Optimal Routing via Short-term Resets
For the linear contextual bandit setup, our algorithm, based on an iterative least squares planner, achieves policy regret $\tilde{O}(\sqrt{dT} + \Delta)$.
Online Learning and Bandits with Queried Hints
For stochastic MAB, we also consider a stronger model where a probe reveals the reward values of the probed arms, and show that in this case, $k=3$ probes suffice to achieve parameter-independent constant regret, $O(n^2)$.
Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment
We study a dynamic traffic assignment model, where agents base their instantaneous routing decisions on real-time delay predictions.
Contextual Recommendations and Low-Regret Cutting-Plane Algorithms
We design algorithms for this problem which achieve regret $O(d\log T)$ and $\exp(O(d \log d))$.
Online Learning under Adversarial Corruptions
We study the design of efficient online learning algorithms tolerant to adversarially corrupted rewards.
Robust Learning for Congestion-Aware Routing
We consider the problem of routing users through a network with unknown congestion functions over an infinite time horizon.
Adaptive Probing Policies for Shortest Path Routing
Inspired by traffic routing applications, we consider the problem of finding the shortest path from a source $s$ to a destination $t$ in a graph, when the lengths of the edges are unknown.
