Related papers: CLAP. I. Resolving miscalibration for deep learnin…
The aim of this paper is to investigate ways to optimize the accuracy of photometric redshifts for a SNAP like mission. We focus on how the accuracy of the photometric redshifts depends on the magnitude limit and signal-to-noise ratio,…
Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty…
As a consequence of galaxy clustering, close galaxies observed on the plane of the sky should be spatially correlated with a probability that is inversely proportional to their angular separation. In principle, this information can be used…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
Anomaly detection is a complex problem due to the ambiguity in defining anomalies, the diversity of anomaly types (e.g., local and global defect), and the scarcity of training data. As such, it necessitates a comprehensive model capable of…
We present accurate photometric redshifts for galaxies observed by the Cluster Lensing and Supernova survey with Hubble (CLASH). CLASH observed 25 massive galaxy cluster cores with the Hubble Space Telescope in 16 filters spanning 0.2 - 1.7…
We present a new method that simultaneously solves for cosmology and galaxy bias on non-linear scales. The method uses the halo model to analytically describe the (non-linear) matter distribution, and the conditional luminosity function…
Previous deep learning approaches for survival analysis have primarily relied on ranking losses to improve discrimination performance, which often comes at the expense of calibration performance. To address such an issue, we propose a novel…
The cross-correlation between 21-cm intensity mapping experiments and photometric surveys of galaxies (or any other cosmological tracer with a broad radial kernel) is severely degraded by the loss of long-wavelength radial modes due to…
Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…
The calibration of redshift distributions for photometric samples using spectroscopic surveys is plagued by the difficulty in modelling the selection functions of spectroscopic surveys. In this work, we analyse how these selection functions…
For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary…
Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…
Accurate and reliable photometric redshift determination is one of the key aspects for wide-field photometric surveys. Determination of photometric redshift for galaxies, has been traditionally solved by use of machine-learning and…
Handling big data has largely been a major bottleneck in traditional statistical models. Consequently, when accurate point prediction is the primary target, machine learning models are often preferred over their statistical counterparts for…
Based on the Sloan Digital Sky Survey Data Release 5 Galaxy Sample, we explore photometric morphology classification and redshift estimation of galaxies using photometric data and known spectroscopic redshifts. An unsupervised method,…
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existing theories fall short in providing explanations for this…
Key science questions, such as galaxy distance estimation and weather forecasting, often require knowing the full predictive distribution of a target variable $y$ given complex inputs $\mathbf{x}$. Despite recent advances in machine…
We use a contrastive self-supervised learning framework to estimate distances to galaxies from their photometric images. We incorporate data augmentations from computer vision as well as an application-specific augmentation accounting for…
Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…