Related papers: Active Learning for Computationally Efficient Dist…
Modern machine learning uses more and more advanced optimization techniques to find optimal hyper parameters. Whenever the objective function is non-convex, non continuous and with potentially multiple local minima, standard gradient…
The energy-efficient control of mobile robots is crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces, which cannot be offset by limited on-board resources. An…
Background: Simulated nucleotide or amino acid sequences are frequently used to assess the performance of phylogenetic reconstruction methods. BEAST, a Bayesian statistical framework that focuses on reconstructing time-calibrated molecular…
The popularity of bi-level optimization (BO) in deep learning has spurred a growing interest in studying gradient-based BO algorithms. However, existing algorithms involve two coupled learning rates that can be affected by approximation…
PySR is an open-source library for practical symbolic regression, a type of machine learning which aims to discover human-interpretable symbolic models. PySR was developed to democratize and popularize symbolic regression for the sciences,…
Accurately measuring stellar ages and internal structures is challenging, but the inclusion of asteroseismic observables can substantially improve precision. However, the curse of dimensionality means this comes at a high computational cost…
Unrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers. Current approaches to optimizing parameters in such computation graphs…
The Laser Interferometer Space Antenna (LISA) will open a new observational window in the millihertz gravitational-wave band, enabling the detection of tens of thousands of compact stellar remnant binaries across the Milky Way. Most of…
High-dimensional deep neural network representations of images and concepts can be aligned to predict human annotations of diverse stimuli. However, such alignment requires the costly collection of behavioral responses, such that, in…
The reconfigurable intelligent surface (RIS) is a promising technology for next-generation wireless communication. It comprises many passive antennas, which reflect signals from the transmitter to the receiver with adjusted phases without…
The effectiveness and stability of mass transfer in binaries system are crucial in determining its final product. Rapid binary population synthesis (BPS) codes simplify the complex physics of mass transfer by adopting parameterized…
Logistic regression is a widely used statistical model to describe the relationship between a binary response variable and predictor variables in data sets. It is often used in machine learning to identify important predictor variables.…
The recent success of deep learning applications has coincided with those widely available powerful computational resources for training sophisticated machine learning models with huge datasets. Nonetheless, training large models such as…
We present an efficient Bayesian method for estimating individual photometric redshifts and galaxy properties under a pre-trained population model (pop-cosmos) that was calibrated using purely photometric data. This model specifies a prior…
Observations of young multiple star systems find a bimodal distribution in companion frequency and separation. The origin of these peaks has often been attributed to binary formation via core and disc fragmentation. However, theory and…
We tackle the fundamental problem of Bayesian active learning with noise, where we need to adaptively select from a number of expensive tests in order to identify an unknown hypothesis sampled from a known prior distribution. In the case of…
As the next generation of large galaxy surveys come online, it is becoming increasingly important to develop and understand the machine learning tools that analyze big astronomical data. Neural networks are powerful and capable of probing…
A new algorithm developed to perform autonomous fitting of gravitational microlensing lightcurves is presented. The new algorithm is conceptually simple, versatile and robust, and parallelises trivially; it combines features of extant…
Recent breakthroughs made by deep learning rely heavily on large number of annotated samples. To overcome this shortcoming, active learning is a possible solution. Beside the previous active learning algorithms that only adopted information…
In this paper, we propose an improved Bayesian bidirectional long-short term memory (BiLSTM) neural networks for multi-step ahead (MSA) solar generation forecasting. The proposed technique applies alpha-beta divergence for a more…