Towards Group Learning: Distributed Weighting of Experts
- URL: http://arxiv.org/abs/2206.02566v1
- Date: Fri, 3 Jun 2022 00:29:31 GMT
- Title: Towards Group Learning: Distributed Weighting of Experts
- Authors: Ben Abramowitz, Nicholas Mattei
- Abstract summary: Aggregating signals from a collection of noisy sources is a fundamental problem in many domains including crowd-sourcing, multi-agent planning, sensor networks, signal processing, voting, ensemble learning, and federated learning.
We build on known results for the optimal weighting of experts and prove that an ensemble of sub-optimal mechanisms can perform optimally under certain conditions.
- Score: 31.564788318133264
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Aggregating signals from a collection of noisy sources is a fundamental
problem in many domains including crowd-sourcing, multi-agent planning, sensor
networks, signal processing, voting, ensemble learning, and federated learning.
The core question is how to aggregate signals from multiple sources (e.g.
experts) in order to reveal an underlying ground truth. While a full answer
depends on the type of signal, correlation of signals, and desired output, a
problem common to all of these applications is that of differentiating sources
based on their quality and weighting them accordingly. It is often assumed that
this differentiation and aggregation is done by a single, accurate central
mechanism or agent (e.g. judge). We complicate this model in two ways. First,
we investigate the setting with both a single judge, and one with multiple
judges. Second, given this multi-agent interaction of judges, we investigate
various constraints on the judges' reporting space. We build on known results
for the optimal weighting of experts and prove that an ensemble of sub-optimal
mechanisms can perform optimally under certain conditions. We then show
empirically that the ensemble approximates the performance of the optimal
mechanism under a broader range of conditions.
Related papers
- Scalable Decentralized Algorithms for Online Personalized Mean Estimation [12.002609934938224]
This study focuses on a simplified version of the overarching problem, where each agent collects samples from a real-valued distribution over time to estimate its mean.
We introduce two collaborative mean estimation algorithms: one draws inspiration from belief propagation, while the other employs a consensus-based approach.
arXiv Detail & Related papers (2024-02-20T08:30:46Z) - Pure Exploration under Mediators' Feedback [63.56002444692792]
Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward.
We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy.
We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
arXiv Detail & Related papers (2023-08-29T18:18:21Z) - On the Complexity of Multi-Agent Decision Making: From Learning in Games
to Partial Monitoring [105.13668993076801]
A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees.
We study this question in a general framework for interactive decision making with multiple agents.
We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making.
arXiv Detail & Related papers (2023-05-01T06:46:22Z) - Resource theory of causal connection [0.5735035463793007]
We build a fully fledged resource theory of causal connection for all multi-party communication scenarios.
We identify the most resourceful processes in the bipartite and tripartite scenarios.
Finally, we introduce a resource theory of causal non-separability, and show that it is -- in contrast to the case of causal connection -- unique.
arXiv Detail & Related papers (2021-10-07T07:33:39Z) - Exploiting Heterogeneity in Robust Federated Best-Arm Identification [19.777265059976337]
Fed-SEL is a simple communication-efficient algorithm that builds on successive elimination techniques and involves local sampling steps at the clients.
We show that for certain heterogeneous problem instances, Fed-SEL outputs the best-arm after just one round of communication.
As our final contribution, we develop variants of Fed-SEL, both for federated and peer-to-peer settings, that are robust to the presence of Byzantine clients.
arXiv Detail & Related papers (2021-09-13T04:22:21Z) - On component interactions in two-stage recommender systems [82.38014314502861]
Two-stage recommenders are used by many online platforms, including YouTube, LinkedIn, and Pinterest.
We show that interactions between the ranker and the nominators substantially affect the overall performance.
In particular, using a Mixture-of-Experts approach, we train the nominators to specialize on different subsets of the item pool.
arXiv Detail & Related papers (2021-06-28T20:53:23Z) - AutoAssign: Differentiable Label Assignment for Dense Object Detection [94.24431503373884]
Auto COCO is an anchor-free detector for object detection.
It achieves appearance-aware through a fully differentiable weighting mechanism.
Our best model achieves 52.1% AP, outperforming all existing one-stage detectors.
arXiv Detail & Related papers (2020-07-07T14:32:21Z) - Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking
Fairness and Algorithm Utility [54.179859639868646]
Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data.
There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups.
We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
arXiv Detail & Related papers (2020-06-15T10:08:39Z) - Public Bayesian Persuasion: Being Almost Optimal and Almost Persuasive [57.47546090379434]
We study the public persuasion problem in the general setting with: (i) arbitrary state spaces; (ii) arbitrary action spaces; (iii) arbitrary sender's utility functions.
We provide a quasi-polynomial time bi-criteria approximation algorithm for arbitrary public persuasion problems that, in specific settings, yields a QPTAS.
arXiv Detail & Related papers (2020-02-12T18:59:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.