Related papers: Dissipative Continuous Spontaneous Localization (C…

Ocean swell plays an important role in the transport of energy across the ocean, yet its evolution is still not well understood. In the late 1960s, the nonlinear Schr{\"o}dinger (NLS) equation was derived as a model for the propagation of…

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…

The hypothesis of the self-induced collapse of the inflaton wave function was introduced as a candidate for the physical process responsible for the emergence of inhomogeneity and anisotropy at all scales. In particular, we consider…

Compressed sensing (CS) is a promising tool for reducing sampling costs. Current deep neural network (NN)-based CS methods face the challenges of collecting labeled measurement-ground truth (GT) data and generalizing to real applications.…

Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this…

Wave function collapse models are considered as the modified theories of standard quantum mechanics at the macroscopic level. By introducing nonlinear stochastic terms in the Schr\"odinger equation, these models make predictions,…

We develop a rigorous treatment of discontinuous stochastic unitary evolution for a system of quantum particles that interacts singularly with quantum "bubbles" at random instants of time. This model of a "cloud chamber" allows to watch and…

What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained…

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic…

Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a…

Non-interferometric experiments have been successfully employed to constrain models of spontaneous wave function collapse, which predict a violation of the quantum superposition principle for large systems. These experiments are grounded on…

State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points. By enforcing such representation to be sparse, sparse subspace clustering is…

In this article we consider the Conditional Super Learner (CSL), an algorithm which selects the best model candidate from a library conditional on the covariates. The CSL expands the idea of using cross-validation to select the best model…

In this work we analyzed the physical origin of the primordial inhomogeneities during the inflation era. The proposed framework is based, on the one hand, on semiclassical gravity, in which only the matter fields are quantized and not the…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

The Gravitational Poissonian Spontaneous Localization (GPSL) model is a hybrid classical-quantum framework in which Newtonian gravity emerges from stochastic collapses of a smeared mass-density operator. Consistency of the hybrid dynamics…

Bassi and Ghirardi have developed a new theory to address the measurement problem based upon non-linear and stochastic modifications of the Schroedinger equation, which has been given the name Quantum Mechanical Spontaneous Localization or…

Collapse models including some external noise of unknown origin are routinely used to describe phenomena on the quantum-classical border; in particular, quantum measurement. Although containing nonlinear dynamics and thereby exposed to the…