Related papers: Towards Robustness Across Cosmological Simulation …

We conduct a systematic robustness analysis of the hybrid machine learning framework \texttt{USmorph}, which integrates unsupervised and supervised learning for galaxy morphological classification. Although \texttt{USmorph} has already been…

Soft, slender structures are ubiquitous in natural and engineered systems, with broad application potential from biomimetic materials to soft robotics. However, there is a notable lack of computational tools that simultaneously preserve…

We present the first-ever cosmological constraints from a simulation-based inference (SBI) analysis of galaxy clustering from the new ${\rm S{\scriptsize IM}BIG}$ forward modeling framework. ${\rm S{\scriptsize IM}BIG}$ leverages the…

We present a novel framework to self-consistently model the effects of radiation fields, dust physics and molecular chemistry (H$_2$) in the interstellar medium (ISM) of galaxies. The model combines a state-of-the-art radiation…

We introduce several new datasets namely ImageNet-A/O and ImageNet-R as well as a synthetic environment and testing suite we called CAOS. ImageNet-A/O allow researchers to focus in on the blind spots remaining in ImageNet. ImageNet-R was…

Studying the impact of systematic effects, optimizing survey strategies, assessing tensions between different probes and exploring synergies of different data sets require a large number of simulated likelihood analyses, each of which cost…

Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic…

Outlying observations can be challenging to handle and adversely affect subsequent analyses, especially in data with increasing dimensional complexity. Although outliers are not always undesired anomalies in the data and may possess…

Quintessence, a scalar field model, has been proposed to account for the acceleration of the Universe at present. We discuss how accurately quintessence models are discriminated by future cosmological surveys, which include experiments of…

Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. When it comes to models directly trained on human faces, a…

Extreme learning machine (ELM) as an emerging branch of shallow networks has shown its excellent generalization and fast learning speed. However, for blended data, the robustness of ELM is weak because its weights and biases of hidden nodes…

End-to-end ASR models, despite their success on benchmarks, often pro-duce catastrophic semantic errors in noisy environments. We attribute this fragility to the prevailing 'direct mapping' objective, which solely penalizes final output…

We present ROBO, a model and its companion code for the study of the interstellar medium (ISM). The aim is to provide an accurate description of the physical evolution of the ISM and to set the ground for an ancillary tool to be inserted in…

We introduce a new code, ECOSMOG, to run N-body simulations for a wide class of modified gravity and dynamical dark energy theories. These theories generally have one or more new dynamical degrees of freedom, the dynamics of which are…

With the growing success of multi-modal learning, research on the robustness of multi-modal models, especially when facing situations with missing modalities, is receiving increased attention. Nevertheless, previous studies in this domain…

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

We present the methodology for deriving accurate and reliable cosmological constraints from non-linear scales (<50Mpc/h) with k-th nearest neighbor (kNN) statistics. We detail our methods for choosing robust minimum scale cuts and…

Many robot control scenarios involve assessing system robustness against a task specification. If either the controller or environment are composed of "black-box" components with unknown dynamics, we cannot rely on formal verification to…

There has been a recent surge of interest in developing generally-capable agents that can adapt to new tasks without additional training in the environment. Learning world models from reward-free exploration is a promising approach, and…

Estimating fluid dynamics is classically done through the simulation and integration of numerical models solving the Navier-Stokes equations, which is computationally complex and time-consuming even on high-end hardware. This is a…