arXiv research

New algorithms reduce communication costs in collaborative learning.

Study collaborative learning among multi-agents in multi-armed bandits.

We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have $k$ players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously. The quality of the col…

New algorithms balance collaboration and adversarial behavior in linear bandits.

Partner-aware algorithms improve AI collaboration in multi-agent settings.

New algorithms for collaborative learning in uncertain, decentralized environments.

Collaborative filtering is a rapidly advancing research area. Every year several new techniques are proposed and yet it is not clear which of the techniques work best and under what conditions. In this paper we conduct a study comparing several collaborative filtering techniques -- both classic and recent state-of-the-…

Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.

There is much empirical evidence that item-item collaborative filtering works well in practice. Motivated to understand this, we provide a framework to design and analyze various recommendation algorithms. The setup amounts to online binary matrix completion, where at each time a random user requests a recommendation a…

In this paper we examine the effect of applying ensemble learning to the performance of collaborative filtering methods. We present several systematic approaches for generating an ensemble of collaborative filtering models based on a single collaborative filtering algorithm (single-model or homogeneous ensemble). We pr…

We study a recent model of collaborative PAC learning where $k$ players with $k$ different tasks collaborate to learn a single classifier that works for all tasks. Previous work showed that when there is a classifier that has very small error on all tasks, there is a collaborative algorithm that finds a single classifi…

New approach to algorithmic fairness for human-AI collaboration considers compliance with human decisions.

New algorithm balances exploration cost between groups in multi-armed bandits.

New algorithm reduces regret in collaborative multi-agent bandit problems.

Advances in collaborative filtering and ranking methods.

A new method for online personalized learning reduces gradient variance by dynamically selecting peers.

Develops NFCF to reduce gender bias in social media recommendation systems.

Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.

In this paper, we propose a listwise approach for constructing user-specific rankings in recommendation systems in a collaborative fashion. We contrast the listwise approach to previous pointwise and pairwise approaches, which are based on treating either each rating or each pairwise comparison as an independent instan…

A framework for collaborative learning reduces communication rounds.

Optimum-statistical collaboration improves black-box optimization efficiency.

New collaborative algorithm improves personalized mean estimation in online settings.

Algorithm maximizes user rewards under per-item budget constraints.

Collaborative recommendation is an information-filtering technique that attempts to present information items (movies, music, books, news, images, Web pages, etc.) that are likely of interest to the Internet user. Traditionally, collaborative systems deal with situations with two types of variables, users and items. In…

This work advances collaborative decision making by combining human and AI strengths in uncertainty quantification.

A novel method for efficient CDRL over wireless networks.

Recommendation systems have been integrated into the majority of large online systems to filter and rank information according to user profiles. It thus influences the way users interact with the system and, as a consequence, bias the evaluation of the performance of a recommendation algorithm computed using historical…

Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.

Asynchronous algorithms reduce privacy costs in distributed machine learning.

New algorithm for collaborative bandit learning reduces sample complexity and regret.

Many businesses are using recommender systems for marketing outreach. Recommendation algorithms can be either based on content or driven by collaborative filtering. We study different ways to incorporate content information directly into the matrix factorization approach of collaborative filtering. These content-booste…

In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood information and have a hard time taking advantage of deeper neighborhoods beyond 1-2 hops. The main caveat of exploiting deeper graph informa…

Framework allows organizations to collaborate on learning tasks securely.

In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality. In this paper, we build on recent algorithmic progresses in distributed deep learning to explore various consensus-optimality trade-offs over a fixed commu…

A new algorithm adapts to changing user behaviors in finance.

In this paper, we address the general case of a coordinated secondary network willing to exploit communication opportunities left vacant by a licensed primary network. Since secondary users (SU) usually have no prior knowledge on the environment, they need to learn the availability of each channel through sensing techn…

AgABC improves ABC algorithm by balancing exploration and exploitation.

Optimizes resource allocation for distributed parameter estimation in sensor networks.

Increased public interest in healthy lifestyles has motivated the study of algorithms that encourage people to follow a healthy diet. Applying collaborative filtering to build recommendation systems in domains where only implicit feedback is available is also a rapidly growing research area. In this report we combine t…

Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limi…

A new algorithm reduces communication costs for collaborative decision-making across clients.

Artificial intelligence (AI) is intrinsically data-driven. It calls for the application of statistical concepts through human-machine collaboration during generation of data, development of algorithms, and evaluation of results. This paper discusses how such human-machine collaboration can be approached through the sta…

Classical collaborative filtering, and content-based filtering methods try to learn a static recommendation model given training data. These approaches are far from ideal in highly dynamic recommendation domains such as news recommendation and computational advertisement, where the set of items and users is very fluid.…

Optimal recommendation system using user and item clustering.

Collab algorithm learns models from agents with missing data.

Framework uses human judgment to distinguish algorithmically indistinguishable cases.

We study the stability vis a vis adversarial noise of matrix factorization algorithm for matrix completion. In particular, our results include: (I) we bound the gap between the solution matrix of the factorization method and the ground truth in terms of root mean square error; (II) we treat the matrix factorization as …

JPS improves joint policies for multi-agent collaboration in imperfect information games.