Search Results for author:
Found 14 papers, 4 papers with code
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
In this paper, we initiate the study of robustness in rank aggregation under the popular Bradley-Terry-Luce (BTL) model for pairwise comparisons.
When Can We Track Significant Preference Shifts in Dueling Bandits?
Specifically, we study the recent notion of significant shifts (Suk and Kpotufe, 2022), and ask whether one can design an adaptive algorithm for the dueling problem with $O(\sqrt{K\tilde{L}T})$ dynamic regret, where $\tilde{L}$ is the (unknown) number of significant shifts in preferences.
Online Recommendations for Agents with Discounted Adaptive Preferences
We give another algorithm for pseudo-increasing models (under a restriction on the adversarial nature of the reward functions), which works for any $\gamma$ and is faster when $\gamma$ is sufficiently small, and we show a super-polynomial regret lower bound with respect to EIRD for general models in the ``small $\gamma$'' regime.
An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem
}$ We answer this in the affirmative $\textit{under the Condorcet condition}$, a standard setting of the $K$-armed dueling bandit problem.
Diversified Recommendations for Agents with Adaptive Preferences
For this class, we give an algorithm for the Recommender which obtains $\tilde{O}(T^{3/4})$ regret against all item distributions satisfying two conditions: they are sufficiently diversified, and they are instantaneously realizable at any history by some distribution over menus.
Sublinear Algorithms for Hierarchical Clustering
At the heart of our algorithmic results is a view of the objective in terms of cuts in the graph, which allows us to use a relaxed notion of cut sparsifiers to do hierarchical clustering while introducing only a small distortion in the objective function.
A Sharp Memory-Regret Trade-Off for Multi-Pass Streaming Bandits
In this paper we study the trade-off between memory and regret when $B$ passes over the stream are allowed, for any $B \geq 1$, and establish tight regret upper and lower bounds for any $B$-pass algorithm.
Batched Dueling Bandits
The $K$-armed dueling bandit problem, where the feedback is in the form of noisy pairwise comparisons, has been widely studied.
Machine learning models for prediction of droplet collision outcomes
Another key question we try to answer in this paper is whether existing knowledge of the physics based models can be exploited to boost the accuracy of the ML classifiers.
Simulation of Vision-based Tactile Sensors using Physics based Rendering
Tactile sensing has seen a rapid adoption with the advent of vision-based tactile sensors.
Robotics Graphics
Choice Bandits
Here we study a natural generalization, that we term \emph{choice bandits}, where the learner plays a set of up to $k \geq 2$ arms and receives limited relative feedback in the form of a single multiway choice among the pulled arms, drawn from an underlying multiway choice model.
Model Learning for Look-ahead Exploration in Continuous Control
We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies .
Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
We propose hand/eye con-trollers that learn to move the camera to keep the object within the field of viewand visible, in coordination to manipulating it to achieve the desired goal, e. g., pushing it to a target location.
Accelerated Spectral Ranking
In this paper, we design a provably faster spectral ranking algorithm, which we call accelerated spectral ranking (ASR), that is also consistent under the MNL/BTL models.
