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.
Machine learning detects type Ia supernovae from photometric data.
Measuring supernova neutrinos removes spacetime's conformal freedom.
Cosmologists are facing the problem of the analysis of a huge quantity of data when observing the sky. The methods used in cosmology are, for the most of them, relying on astrophysical models, and thus, for the classification, they usually use a machine learning approach in two-steps, which consists in, first, extracti…
CNNs improve transient detection in DES-SN images.
DiTSNe-Ia model accurately reconstructs supernovae spectra from light curves.
The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where domain adaptation is a popular scenario. An example is to build a predictive model on…
In the present work, torsion energy is defined. Its law of conservation is given. It is shown that this type of energy gives rise to a repulsive force which can be used to interpret supernovae type Ia observations, and consequently the accelerating expansion of the Universe. This interpretation is a pure geometric one …
Cross-validation (CV) is a technique for evaluating the ability of statistical models/learning systems based on a given data set. Despite its wide applicability, the rather heavy computational cost can prevent its use as the system size grows. To resolve this difficulty in the case of Bayesian linear regression, we dev…
Ensemble methods for supervised machine learning have become popular due to their ability to accurately predict class labels with groups of simple, lightweight "base learners." While ensembles offer computationally efficient models that have good predictive capability they tend to be large and offer little insight into…
Proposes a method to improve learning when training data is not representative.
In previous work a relation between a large class of Kac-Moody algebras and meromorphic connections on global curves was established---notably the Weyl group gives isomorphisms between different moduli spaces of connections, and the root system is also seen to play a role. This involved a modular interpretation of many…
We propose a K-sparse exhaustive search (ES-K) method and a K-sparse approximate exhaustive search method (AES-K) for selecting variables in linear regression. With these methods, K-sparse combinations of variables are tested exhaustively assuming that the optimal combination of explanatory variables is K-sparse. By co…
Predicts the age of astronomical transients from real-time data.
Detects anomalies in astronomical time series data.
We present the first evidence that adaptive learning techniques can boost the discovery of unusual objects within astronomical light curve data sets. Our method follows an active learning strategy where the learning algorithm chooses objects which can potentially improve the learner if additional information about them…
Genetic algorithms optimize neural networks for cosmological data analysis.
SDIFT generates full-field dynamics from sparse, irregular data.
LSVM with EBT reduces quasar detection errors by 10x.