A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logge…
We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine tra…
We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of K actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problem…
New learning methods for open systems with variable agents.
problem Learning in open systems with dynamic agent arrivals and departures.
method Formulated a unified open-system bandit problem with general dynamics, introducing new concepts like pre-training degree and stability.
result Certified global-UCB learning methodologies with provable guarantees, revealing dependencies between entry uncertainty, stability, and agent patterns.
We study the problem of regret minimization for distributed bandits learning, in which M agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the…
This article introduces the concepts around Online Bandit Linear Optimization and explores an efficient setup called SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a O(T) regret bound and polynomial run time comple…
We use surrogate losses to obtain several new regret bounds and new algorithms for contextual bandit learning. Using the ramp loss, we derive new margin-based regret bounds in terms of standard sequential complexity measures of a benchmark class of real-valued regression functions. Using the hinge loss, we derive an ef…
We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…
We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm t…
In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support. While our current use cases focus on single step einforcement learning (RL) and mostly in the domain of natural language proce…
A new method for energy-efficient file delivery in small cell networks.
problem Efficient resource management in femto-caching with time-variant statistical properties.
method Formulates a resource allocation problem as a stochastic knapsack problem and a multi-armed bandit problem, developing solutions for each.
result The proposed method maximizes the accumulated utility over the horizon, especially suitable for networks with time-variant statistical properties.
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…
In many platforms, user arrivals exhibit a self-reinforcing behavior: future user arrivals are likely to have preferences similar to users who were satisfied in the past. In other words, arrivals exhibit positive externalities. We study multiarmed bandit (MAB) problems with positive externalities. We show that the self…
This work introduces reward teaching for federated multi-armed bandits to guide clients towards global optimality.
problem Existing federated multi-armed bandits designs assume clients will follow the server's protocol, but this is not always feasible.
method Introduces reward teaching where the server adjusts clients' local rewards to encourage global optimality, using phased Teaching-After-Learning (TAL) and Teaching-While-Learning (TWL) algorithms.
result Demonstrates that TAL achieves logarithmic regrets with only logarithmic adjustment costs, and TWL outperforms TAL for UCB1 clients.
A popular approach to selling online advertising is by a waterfall, where a publisher makes sequential price offers to ad networks for an inventory, and chooses the winner in that order. The publisher picks the order and prices to maximize her revenue. A traditional solution is to learn the demand model and then subseq…
Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsa…
Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically …