Related papers: Star-specific Key-homomorphic PRFs from Learning w…

The WHT Enhanced Area Velocity Explorer (WEAVE) is a new, massively multiplexing spectrograph. This new instrument will be exploited to obtain high S/N spectra of $\sim$25000 galaxies at intermediate redshifts for the WEAVE Stellar…

(abridged) We develop a tool for the automated spectral classification of OB stars according to their sub-types. We use the regular Random Forest (RF) algorithm, the Probabilistic RF (PRF), and we introduce the KDE-RF method which is a…

We define a pseudorandom function (PRF) $F: \mathcal{K} \times \mathcal{X} \rightarrow \mathcal{Y}$ to be bi-homomorphic when it is fully Key homomorphic and partially Input Homomorphic (KIH), i.e., given $F(k_1, x_1)$ and $F(k_2, x_2)$,…

Radio wavelengths offer a unique possibility to trace the total star-formation rate (SFR) in galaxies, both obscured and unobscured. To probe the dust-unbiased star-formation history, an accurate measurement of the radio luminosity function…

We introduce a new method for solving maximum likelihood problems through variational calculus, and apply it to the case of recovering an unknown star formation history, $SFR(t)$, from a resulting HR diagram. This approach allows a totally…

We propose a random feature model for approximating high-dimensional sparse additive functions called the hard-ridge random feature expansion method (HARFE). This method utilizes a hard-thresholding pursuit-based algorithm applied to the…

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here, we focus on two prevalent methods used to align these…

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In…

It is critical yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments. Although a lot of efforts have been made, such as heteroscedastic neural networks (HNNs), little work…

Inspired by the recently remarkable successes of Sparse Representation (SR), Collaborative Representation (CR) and sparse graph, we present a novel hypergraph model named Regression-based Hypergraph (RH) which utilizes the regression models…

We use recent HST colour-magnitude diagrams of the resolved stellar populations of a sample of local dSph galaxies (Carina, LeoI, LeoII, Ursa Minor and Draco) to infer the star formation histories of these systems, $SFR(t)$. Applying a new…

Methods that sparsify a network at initialization are important in practice because they greatly improve the efficiency of both learning and inference. Our work is based on a recently proposed decomposition of the Neural Tangent Kernel…

Modeling non-stationary processes, where statistical properties vary across the input domain, is a critical challenge in machine learning; yet most scalable methods rely on a simplifying assumption of stationarity. This forces a difficult…

Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable…

We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). Our analysis shows that when the true reward function is linear, the widely used maximum likelihood estimator (MLE) converges under both the…

Neural-network based predictions of event properties in astro-particle physics are getting more and more common. However, in many cases the result is just utilized as a point prediction. Statistical uncertainties, coverage, systematic…

While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable spurious features rather than the core features that are genuinely correlated to the true label. In this…

We derive a family of linear inference algorithms that generalize existing graph-based label propagation algorithms by allowing them to propagate generalized assumptions about "attraction" or "compatibility" between classes of neighboring…

A fundamental challenge for wide-field imaging surveys is obtaining follow-up spectroscopic observations: there are > $10^9$ photometrically cataloged sources, yet modern spectroscopic surveys are limited to ~few x $10^6$ targets. As we…