Related papers: Does Lorentz-symmetric design boost network perfor…
Jets with a large radius $R\gtrsim 1$ and grooming algorithms are widely used to fully capture the decay products of boosted heavy particles at the Large Hadron Collider (LHC). Unlike most discriminating variables used in such studies, the…
Jets from boosted heavy particles have a typical angular scale which can be used to distinguish them from QCD jets. We introduce a machine learning strategy for jet substructure analysis using a spectral function on the angular scale. The…
The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn, stimulated a significant improvement in the hardware…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
Latent space models are powerful statistical tools for modeling and understanding network data. While the importance of accounting for uncertainty in network analysis has been well recognized, the current literature predominantly focuses on…
Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where…
Learning-based planners leveraging Graph Neural Networks can learn search guidance applicable to large search spaces, yet their potential to address symmetries remains largely unexplored. In this paper, we introduce a graph representation…
Most real-world networks are embedded in latent geometries. If a node in a network is found in the vicinity of another node in the latent geometry, the two nodes have a disproportionately high probability of being connected by a link. The…
The existence of considerable amount of redundancy in the Internet traffic at the packet level has stimulated the deployment of packet-level redundancy elimination techniques within the network by enabling network nodes to memorize data…
Latent space models are frequently used for modeling single-layer networks and include many popular special cases, such as the stochastic block model and the random dot product graph. However, they are not well-developed for more complex…
Distances are pervasive in machine learning. They serve as similarity measures, loss functions, and learning targets; it is said that a good distance measure solves a task. When defining distances, the triangle inequality has proven to be a…
Recently, machine learning has been used in every possible field to leverage its amazing power. For a long time, the net-working and distributed computing system is the key infrastructure to provide efficient computational resource for…
Qualitatively new aspects of the (linear and non-linear) stability of sheared relativistic (slab) jets are analyzed. The linear problem has been solved for a wide range of jet models well inside the ultrarelativistic domain (flow Lorentz…
Models applied on real time response task, like click-through rate (CTR) prediction model, require high accuracy and rigorous response time. Therefore, top-performing deep models of high depth and complexity are not well suited for these…
We present Hinted Networks: a collection of architectural transformations for improving the accuracies of neural network models for regression tasks, through the injection of a prior for the output prediction (i.e. a hint). We ground our…
We show a monotonic relationship between performances of various computer vision tasks versus degrees of coherence of illumination. We simulate partially coherent illumination using computational methods, propagate the lightwave to form…
Attention-based transformer models have become increasingly prevalent in collider analysis, offering enhanced performance for tasks such as jet tagging. However, they are computationally intensive and require substantial data for training.…
Point cloud completion networks are conventionally trained to minimize the disparities between the completed point cloud and the ground-truth counterpart. However, an incomplete object-level point cloud can have multiple valid completion…
Discovering a high-performing sparse network within a massive neural network is advantageous for deploying them on devices with limited storage, such as mobile phones. Additionally, model explainability is essential to fostering trust in…
We explore the challenging but phenomenologically interesting hierarchical mass spectrum of the Inert Doublet Model where relatively light dark matter along with much heavier scalar states can fully satisfy the constraints on the relic…