Search Results for author:
Found 20 papers, 1 papers with code
Fair Exploration and Exploitation
At the start of each trial we are given a probability distribution over the context set and are required (on that trial) to be fair with respect to that distribution, in that if the context (for that trial) was drawn from the distribution then our choice of action would be unbiased towards any protected group.
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
A switching regret is defined relative to any segmentation of the trial sequence, and is equal to the sum of the static regrets of each segment.
Extraction Propagation
Running backpropagation end to end on large neural networks is fraught with difficulties like vanishing gradients and degradation.
Bandits with Abstention under Expert Advice
We study the classic problem of prediction with expert advice under bandit feedback.
A Hierarchical Nearest Neighbour Approach to Contextual Bandits
In this paper we consider the adversarial contextual bandit problem in metric spaces.
Sum-max Submodular Bandits
Many online decision-making problems correspond to maximizing a sequence of submodular functions.
Nearest Neighbour with Bandit Feedback
In this paper we adapt the nearest neighbour rule to the contextual bandit problem.
Adversarial Online Collaborative Filtering
We investigate the problem of online collaborative filtering under no-repetition constraints, whereby users need to be served content in an online fashion and a given user cannot be recommended the same content item more than once.
Joint Coreset Construction and Quantization for Distributed Machine Learning
Coresets are small, weighted summaries of larger datasets, aiming at providing provable error bounds for machine learning (ML) tasks while significantly reducing the communication and computation costs.
A Gang of Adversarial Bandits
Users are in a social network and the learner is aided by a-priori knowledge of the strengths of the social links between all pairs of users.
Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback
This paper studies a cooperative multi-armed bandit problem with $M$ agents cooperating together to solve the same instance of a $K$-armed stochastic bandit problem with the goal of maximizing the cumulative reward of agents.
Communication-efficient k-Means for Edge-based Machine Learning
We consider the problem of computing the k-means centers for a large high-dimensional dataset in the context of edge-based machine learning, where data sources offload machine learning computation to nearby edge servers.
Online Multitask Learning with Long-Term Memory
We provide an algorithm that predicts on each trial in time linear in the number of hypotheses when the hypothesis class is finite.
Online Learning of Facility Locations
In this paper, we provide a rigorous theoretical investigation of an online learning version of the Facility Location problem which is motivated by emerging problems in real-world applications.
Online Matrix Completion with Side Information
In this setting, we provide an example where the side information is not directly specified in advance.
MaxHedge: Maximising a Maximum Online
We introduce a new online learning framework where, at each trial, the learner is required to select a subset of actions from a given known action set.
On Pairwise Clustering with Side Information
We measure performance not based on the recovery of the hidden similarity function, but instead on how well we classify each item.
Mistake Bounds for Binary Matrix Completion
We study the problem of completing a binary matrix in an online learning setting.
Online Prediction at the Limit of Zero Temperature
We design an online algorithm to classify the vertices of a graph.
A Time and Space Efficient Junction Tree Architecture
The junction tree algorithm first constructs a tree called a junction tree who's vertices are sets of random variables.
