arXiv research

Proposes a method to cluster tasks for constructive cooperative multi-tasking.

Enhances cooperative multi-task SemCom for distributed users.

The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature). Renowned Bayesian approaches for cooperative hierarchical structure modeling are mostly bas…

Analyzes gaming in federated learning systems and provides design principles.

Paper explores alternative cooperative game theory methods for machine learning feature attribution.

Develops methods for cooperative Bayesian inference.

Study finds root vertex in large networks with high probability.

Multi-cell cooperative processing with limited backhaul traffic is studied for cellular uplinks. Aiming at reduced backhaul overhead, a sparsity-regularized multi-cell receive-filter design problem is formulated. Both unstructured distributed cooperation as well as clustered cooperation, in which base station groups ar…

Develops an equilibrium model for securities pricing in a mixed cooperative and non-cooperative market.

Income redistribution is the transfer of income from some individuals to others directly or indirectly by means of social mechanisms, such as taxation, public services and so on. Employing a spatial public goods game, we study the influence of income redistribution on the evolution of cooperation. Two kinds of evolutio…

Stable cooperation emerges in fluctuating environments.

The paper tackles cooperative RL with function approximation, achieving near-optimal learning with limited communication.

We study the explore-exploit tradeoff in distributed cooperative decision-making using the context of the multiarmed bandit (MAB) problem. For the distributed cooperative MAB problem, we design the cooperative UCB algorithm that comprises two interleaved distributed processes: (i) running consensus algorithms for estim…

CSAC enables cooperative reinforcement learning for multi-stage tasks.

Cooperation is a persistent behavioral pattern of entities pooling and sharing resources. Its ubiquity in nature poses a conundrum. Whenever two entities cooperate, one must willingly relinquish something of value to the other. Why is this apparent altruism favored in evolution? Classical solutions assume a net fitness…

Cooperative communication plays a central role in theories of human cognition, language, development, culture, and human-robot interaction. Prior models of cooperative communication are algorithmic in nature and do not shed light on why cooperation may yield effective belief transmission and what limitations may arise …

New strategy achieves optimal regret without communication or collisions in multi-player bandit.

Facing a heavy task, any single person can only make a limited contribution and team cooperation is needed. As one enjoys the benefit of the public goods, the potential benefits of the project are not always maximized and may be partly wasted. By incorporating individual ability and project benefit into the original pu…

New method combines heuristics and search techniques to speed up cooperative planning for autonomous vehicles.

Kernel method improves cooperative decision-making among agents.

New particle-based method improves semi-supervised learning robustness to label noise.

Framework for games with uncertain parameters, ensuring no player can improve by changing strategy.

We consider in a market model the cooperative emergence of value due to a positive feedback between perception of needs and demand. Here we consider also a negative feedback from production of the traded products, and find that this cooperativity is robust, provided that the production rate is slow. Cooperativity is fo…

We construct a new grading on the Goldman Lie algebra of a closed oriented surface by the winding number. This grading induces a grading on the HOMFLY-PT skein algebra and related algebras. Our work supports the conjectures of B. Cooper and P. Samuelson

A new algorithm reduces regret in cooperative multi-agent bandits with heavy-tailed data.

New algorithm reduces individual regret and communication costs in cooperative bandits.

Cooperation information sharing is important to theories of human learning and has potential implications for machine learning. Prior work derived conditions for achieving optimal Cooperative Inference given strong, relatively restrictive assumptions. We relax these assumptions by demonstrating convergence for any disc…

Asynchronous cooperative learning rules ensure all agents converge to correct hypothesis.

Study shows cooperation can improve everyone's market efficiency.

A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient explo…

Cooper-Manning and Louder gave examples of maps of surface groups to PSL(2,C) which are not injective, but are incompressible (i.e. no simple loop is in the kernel). We construct more examples with very simple certificates for their incompressibility arising from the theory of stable commutator length.

Maker-taker fees can prevent algorithmic cooperation in market making, but not always.

For an arbitrary positive integer n, we construct infinitely many one-cusped hyperbolic 3-manifolds where each manifold's A-polynomial detects every n-th root of unity. This answers a question of Cooper, Culler, Gillet, Long, and Shalen as to which roots of unity arise in this manner.

ComEx protocol reduces communication costs in cooperative bandits.

We discuss a new perspective on Khovanov homology, using categorifications of tensor products. While in many ways more technically demanding than Khovanov's approach (and its extension by Bar-Natan), this has distinct advantage of directly connecting Khovanov homology to a categorification of \$(\mathbb{C}^2)^{\otimes …

A new method for combining multiple data views in supervised learning.

Hierarchies of temporally decoupled policies present a promising approach for enabling structured exploration in complex long-term planning problems. To fully achieve this approach an end-to-end training paradigm is needed. However, training these multi-level policies has had limited success due to challenges arising f…

Study how communication and feedback graphs affect learning outcomes.

Study shows market makers can cooperate without communication.

New cooperative dynamics enhances retrieval performance in neural networks.

Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interp…

Paper develops a private algorithm for multi-agent learning in bandits.

The paper extends collective arbitrage concepts to multi-agent markets with cooperation.

Study shows cooperation can reduce investment risk and price gaps.

New method attributes feature uncertainty in ML models using cooperative game theory.

Adversaries can manipulate cooperative MARL networks.

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

Introduces LTQL for factored policies in cooperative MARL.