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.
No communication allows optimal instance-dependent regret guarantees in multi-player bandits.
Across many scientific domains, there is a common need to automatically extract a simplified view or coarse-graining of how a complex system's components interact. This general task is called community detection in networks and is analogous to searching for clusters in independent vector data. It is common to evaluate …
The paper tackles cooperative RL with function approximation, achieving near-optimal learning with limited communication.
The problem of community detection in networks is usually formulated as finding a single partition of the network into some "correct" number of communities. We argue that it is more interpretable and in some regimes more accurate to construct a hierarchical tree of communities instead. This can be done with a simple to…
Modularity is a popular measure of community structure. However, maximizing the modularity can lead to many competing partitions, with almost the same modularity, that are poorly correlated with each other. It can also produce illusory "communities" in random graphs where none exist. We address this problem by using th…
New algorithms tackle adversarial multi-player bandits with forced-collision communication.
New algorithms reduce communication costs in collaborative learning.
New strategy achieves optimal regret without communication or collisions in multi-player bandit.
New method compares community detection algorithms without ground truth.
New algorithm for multi-player bandits with collision-dependent rewards.
One-layer transformers can't solve induction heads task efficiently.
A common data mining task on networks is community detection, which seeks an unsupervised decomposition of a network into structural groups based on statistical regularities in the network's connectivity. Although many methods exist, the No Free Lunch theorem for community detection implies that each makes some kind of…
AdaQuantFL reduces communication in federated learning by adaptively quantizing model updates.
Study shows it's impossible to count communities without finding them.
We introduce a new paradigm that is important for community detection in the realm of network analysis. Networks contain a set of strong, dominant communities, which interfere with the detection of weak, natural community structure. When most of the members of the weak communities also belong to stronger communities, t…
We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared t…
Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming algorithms, we introduce Sketched SGD, an algorithm for carrying out distributed SGD by c…
A new model for detecting overlapping communities in weighted networks.
EF21-Muon optimizes deep learning with error feedback, improving efficiency and accuracy.
New model detects communities in networks with signed, continuous weights.
Social media systems rely on user feedback and rating mechanisms for personalization, ranking, and content filtering. However, when users evaluate content contributed by fellow users (e.g., by liking a post or voting on a comment), these evaluations create complex social feedback effects. This paper investigates how ra…
Graph energy helps detect communities in networks better than traditional methods.
We consider two agents playing simultaneously the same stochastic three-armed bandit problem. The two agents are cooperating but they cannot communicate. We propose a strategy with no collisions at all between the players (with very high probability), and with near-optimal regret . We also argue th…
We study the fundamental limits on learning latent community structure in dynamic networks. Specifically, we study dynamic stochastic block models where nodes change their community membership over time, but where edges are generated independently at each time step. In this setting (which is a special case of several e…
We consider a variant of the stochastic multi-armed bandit problem, where multiple players simultaneously choose from the same set of arms and may collide, receiving no reward. This setting has been motivated by problems arising in cognitive radio networks, and is especially challenging under the realistic assumption t…
Paper models graph edge dependencies using latent variables for community detection.
Bottom-up algorithms outperform top-down in hierarchical community detection at intermediate levels.
To date, most studies on spam have focused only on the spamming phase of the spam cycle and have ignored the harvesting phase, which consists of the mass acquisition of email addresses. It has been observed that spammers conceal their identity to a lesser degree in the harvesting phase, so it may be possible to gain ne…
In distributed statistical learning, samples are split across machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. Howev…
Most of the current complex networks that are of interest to practitioners possess a certain community structure that plays an important role in understanding the properties of these networks. Moreover, many machine learning algorithms and tools that are developed for complex networks try to take advantage of the exist…
The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper. Building on the seminal work of Boursier and Perchet (2019), we propose error correction synchronization involving communication (EC-SIC), whose regre…
The paper addresses the Multiplayer Multi-Armed Bandit (MMAB) problem, where decision makers or players collaborate to maximize their cumulative reward. When several players select the same arm, a collision occurs and no reward is collected on this arm. Players involved in a collision are informed about this collis…
TransNet improves community detection on target networks using privacy-preserved source networks.
Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at the same stage. We present a decentralized algorithm that achieves the same performance as a centra…
Efficient algorithm for matching graphs with community structure.
This paper analyzes the trade-off between accuracy and communication in personalized federated learning.
The Gradient Boosted Tree (GBT) algorithm is one of the most popular machine learning algorithms used in production, for tasks that include Click-Through Rate (CTR) prediction and learning-to-rank. To deal with the massive datasets available today, many distributed GBT methods have been proposed. However, they all assu…
In principle, higher-order networks that have multiple edge types are more informative than their lower-order counterparts. In practice, however, excessively rich information may be algorithmically infeasible to extract. It requires an algorithm that assumes a high-dimensional model and such an algorithm may perform po…
Study examines financial contagion at community level, finding increased contagion density and widespread transmission.
Study proves consistency of spectral clustering on hierarchical networks.
We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of agents, solving the same MAB instance to minimize individual cumulative regret. In our model, agents collaborate by exchanging messages through pairwise gossip style communications on an arbitrary connected graph. We develop two no…
A new method for distributed optimization reduces communication rounds without minibatches.
FedNew improves federated learning efficiency and privacy.
Proposes a method for coarse graph alignment using sparse partial least squares.
Algorithm ensures fair information spread in social networks with community structure.
Handling the tremendous amount of network data, produced by the explosive growth of mobile traffic volume, is becoming of main priority to achieve desired performance targets efficiently. Opportunistic communication such as FloatingContent (FC), can be used to offload part of the cellular traffic volume to vehicular-to…
A genetic algorithm with community detection improves feature selection accuracy.
The Stochastic Block Model (SBM) is a widely used random graph model for networks with communities. Despite the recent burst of interest in recovering communities in the SBM from statistical and computational points of view, there are still gaps in understanding the fundamental information theoretic and computational l…