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.
Edge augmentation connects disconnected graphs by elevating eigenvalues.
Generative model for creating graphs with new communities.
Much of the data being created on the web contains interactions between users and items. Stochastic blockmodels, and other methods for community detection and clustering of bipartite graphs, can infer latent user communities and latent item clusters from this interaction data. These methods, however, typically ignore t…
A new decentralized algorithm DESTINY solves optimization over Stiefel manifold with single communication round.
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communicati…
A new method solves distributed optimization problems over networks.
Fed-TDA augments federated tabular data to improve performance and privacy.
The stochastic block model (SBM) is a probabilistic model for community structure in networks. Typically, only the adjacency matrix is used to perform SBM parameter inference. In this paper, we consider circumstances in which nodes have an associated vector of continuous attributes that are also used to learn the node-…
A hierarchical gamma process infinite edge partition model is proposed to factorize the binary adjacency matrix of an unweighted undirected relational network under a Bernoulli-Poisson link. The model describes both homophily and stochastic equivalence, and is scalable to big sparse networks by focusing its computation…
Proposes a method to generate high-quality candlestick data for financial trading.
We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward withou…
New method detects communities in hypergraphs by embedding them into a vector space.
How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication a…
A new training method speeds up ResNet training by 3x with minimal accuracy loss.
Augmented KRnet improves flow-based generative modeling by maintaining exact invertibility.
New framework for dense weighted networks with community-specific patterns.
New model for community detection with side information improves recovery accuracy.
This work explains how tempering improves Bayesian neural networks by reducing the impact of data augmentation.
The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error…
Unified framework detects dynamic community structure in brain networks across individuals.
This study compares GNNs and GA-MLPs, finding GA-MLPs can distinguish graphs but not count walks.
Traditionally, community detection in graphs can be solved using spectral methods or posterior inference under probabilistic graphical models. Focusing on random graph families such as the stochastic block model, recent research has unified both approaches and identified both statistical and computational detection thr…
Paper proposes distributed optimization for federated learning with theoretical guarantees.
In this paper, we empirically evaluate algorithms for learning four types of Bayesian network (BN) classifiers - Naive-Bayes, tree augmented Naive-Bayes, BN augmented Naive-Bayes and general BNs, where the latter two are learned using two variants of a conditional-independence (CI) based BN-learning algorithm. Experime…
The behaviors of patients with depression are usually difficult to predict because the patients demonstrate the symptoms of a depressive episode without a warning at unexpected times. The goal of this research is to build algorithms that detect signals of such unusual moments so that doctors can be proactive in approac…
There has been an increasing interest in the area of emergent communication between agents which learn to play referential signalling games with realistic images. In this work, we consider the signalling game setting of Havrylov and Titov and investigate the effect of the feature extractor's weights and of the task bei…
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performanc…
Recent research has helped to cultivate growing awareness that machine learning systems fueled by big data can create or exacerbate troubling disparities in society. Much of this research comes from outside of the practicing data science community, leaving its members with little concrete guidance to proactively addres…
Two methods reduce BN and DNN complexity, balancing size and accuracy.
A method for community detection in multilayer networks using data matrices.
We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance o…
SMP model preserves proximity and permutation in graph neural networks.
Recent years have witnessed the emergence and increasing popularity of 3D medical imaging techniques with the development of 3D sensors and technology. However, achieving geometric invariance in the processing of 3D medical images is computationally expensive but nonetheless essential due to the presence of possible er…
Unified meta-learning framework from supervised learning.
Importance of visual context in scene understanding tasks is well recognized in the computer vision community. However, to what extent the computer vision models for image classification and semantic segmentation are dependent on the context to make their predictions is unclear. A model overly relying on context will f…
ACERL embeds networks into a low-dimensional space preserving structural and semantic properties.
Paper improves compressed SGD to reach second-order stationary points.
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fish…
Study examines how data augmentation impacts optimization in linear regression.
Data augmentation doesn't improve robustness, contrary to belief.
This paper improves auto-augment efficiency by sharing augmentation weights.
Simple policy search outperforms advanced learnable test-time augmentation techniques.
New measures quantify how data augmentation improves model performance.
CNNs encode data augmentation transformations, especially in early layers.
WeMix improves data augmentation by correcting bias in deep learning.
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real examples, such adversarial examples could change the prediction of many of the be…
A study on optimizing data augmentation weights for improved test-time predictions.
Data augmentation can achieve the same statistical benefits as full augmentation up to an approximation error.