Hilbert space
PulseAugur coverage of Hilbert space — every cluster mentioning Hilbert space across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
New Hopfield Networks Achieve 10x Capacity Boost Using SU(d) Groups
Researchers have introduced generalized Hopfield networks that utilize continuous variables on Riemannian manifolds, specifically focusing on symmetric spaces associated with special unitary groups SU(d). This new appro…
-
Hybrid Quantum CNN enhances volcanic thermal activity recognition
Researchers have developed a novel Hybrid Quantum AlexNet architecture designed to improve the recognition of volcanic thermal activity from satellite imagery. This model integrates a classical convolutional neural netw…
-
New framework uses Hilbert space for multi-dimensional reinforcement learning
A new research paper introduces KE-DRL, a framework for multi-dimensional distributional reinforcement learning that utilizes Hilbert space mappings. This approach estimates the kernel mean embedding of multi-dimensiona…
-
New Nesterov acceleration methods developed for probability measures
Researchers have developed new accelerated optimization methods for probability measures, drawing inspiration from Nesterov's accelerated gradient method in Euclidean space. These methods, including Heavy-ball and Neste…
-
Two arXiv papers detail learning dynamical systems from single trajectories · 2 sources tracked
Two new research papers submitted to arXiv's stat.ML section explore the learning of dynamical systems from single trajectories. The first paper focuses on switched non-linear dynamical systems, providing theoretical gu…
-
Quantum Reservoir Computing advances explored in new research papers
Two new research papers explore the field of Quantum Reservoir Computing (QRC), a technique that leverages quantum systems for computation by separating parameter updates from readout. The first paper provides a compreh…
-
New theory explores distributional reinforcement learning under Cramér geometry
Researchers have developed a new theoretical framework for distributional reinforcement learning combined with maximum-entropy control. This work focuses on the Cramér geometry, a metric based on cumulative distribution…
-
Quantum AI research questions scaling hypothesis for program generation
A new position paper argues that current AI scaling hypotheses, which assume increasing parameters lead to emergent reasoning, are misapplied to quantum program generation. The authors contend that unlike natural langua…
-
Quantum computing enhances vision-language model fine-tuning with MQAdapter
Researchers have introduced MQAdapter, a novel approach for fine-tuning vision-language models (VLMs) that utilizes quantum computation. This method aims to improve fine-grained discrimination in few-shot classification…
-
New Superstate Quantum Mechanics theory bridges physics and AI
A new theoretical framework called Superstate Quantum Mechanics (SQM) has been introduced, which expands upon traditional quantum mechanics by considering states in Hilbert space with multiple quadratic constraints. Thi…
-
New framework breaks one-dimensional expressibility-trainability tradeoff in quantum circuits
Researchers have demonstrated that the expressibility and trainability of parameterized quantum circuits (PQCs) are not bound by a one-dimensional tradeoff. They propose a new framework that separates entangling power (…
-
New PCA method for probability measures reveals sparse-dense sampling transition
Researchers have developed a new method for performing Principal Component Analysis (PCA) on probability measures by embedding them into a Hilbert space. This approach addresses the challenge of analyzing multiple measu…
-
OnlyDense framework unifies deep learning with reduced-order modeling
Researchers have developed a novel deep learning framework called OnlyDense to model complex Lagrangian simulations, which are often computationally intensive. This method represents the system's state as a function evo…
-
Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space
Researchers have introduced a novel complex-valued sequence model called Phase-Associative Memory (PAM) that utilizes a Hilbert space formalism to better capture the indeterminate nature of semantic expression meaning. …
-
Quantum CNN predicts glioblastoma methylation status with high accuracy
Researchers have developed a novel quantum convolutional neural network (IA-QCNN) designed to predict MGMT promoter methylation status in glioblastoma patients. This quantum-based approach leverages principles like supe…
-
Researchers develop SGD algorithms for learning operators with operator-valued kernels
Researchers have developed a new method for estimating regression operators in statistical inverse problems. The approach utilizes regularized stochastic gradient descent (SGD) with operator-valued kernels, offering dim…