Related papers: Active learning BSM parameter spaces
Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability. We propose SLM -- Sparse Learnable Masks -- a canonical approach for end-to-end…
Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several…
Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a…
Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each model is specialized to perform a task in a particular domain. Generally, a high labeling effort is required in MDL, as data needs to be labeled by…
This paper proposes asal, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence,…
The goal of this paper is to simulate the benefits of jointly applying active learning (AL) and semi-supervised training (SST) in a new speech recognition application. Our data selection approach relies on confidence filtering, and its…
After the observation in 2012 of a new scalar particle closely resembling the Higgs boson of the Standard Model of particle physics, there is a general consensus that there must be Physics Beyond the Standard Model, with present experiments…
Active learning is a valuable tool for efficiently exploring complex spaces, finding a variety of uses in materials science. However, the determination of convex hulls for phase diagrams does not neatly fit into traditional active learning…
Using a Markov chain Monte Carlo approach, we find the allowed parameter space of a MSSM model with seven free parameters. In this model universality conditions at the GUT scale are imposed on the gaugino sector. We require in particular…
The Alpha Magnetic Spectrometer (AMS) experiment has released new measurements of primary and secondary nuclei in cosmic rays at the TeV energy scale. Using these data, we present new results based on a global Bayesian analysis of our two…
Active learning is usually applied to acquire labels of informative data points in supervised learning, to maximize accuracy in a sample-efficient way. However, maximizing the accuracy is not the end goal when the results are used for…
Active matter refers to systems composed of self-propelled entities that consume energy to produce motion, exhibiting complex non-equilibrium dynamics that challenge traditional models. With the rapid advancements in machine learning,…
We construct a simple U(1) hidden sector model of metastable dark matter that could explain excess 511 keV gamma rays from the galactic center as observed by INTEGRAL, through inelastic scattering of dark matter followed by its decay.…
The ATLAS detector has begun the search for new physics beyond the Standard Model (BSM) with \int L dt = ~45 pb^-1 of data collected in 2010. After no significant evidence of new physics was found in the data, limits on possible signatures…
Active learning is typically used to label data, when the labeling process is expensive. Several active learning algorithms have been theoretically proved to perform better than their passive counterpart. However, these algorithms rely on…
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language…
Recently a model has been proposed that links dark matter and neutrino masses. The dark matter candidate which is dubbed as SLIM has a mass of MeV scale and can show up at low energy experiments. The model also has a high energy sector…
Active learning, an iterative process of selecting the most informative data points for exploration, is crucial for efficient characterization of materials and chemicals property space. Neural networks excel at predicting these properties…
Galactic dark matter may consist of axionlike particles (ALPs) that can be described as an "ultralight bosonic field" oscillating at the ALP Compton frequency. The ALP field can be searched for using nuclear magnetic resonance (NMR), where…
We compare updated predictions for the elastic scattering of supersymmetric neutralino dark matter with the improved experimental upper limit recently published by CDMS II. We take into account the possibility that the \pi-nucleon \Sigma…