compressed sensing
PulseAugur coverage of compressed sensing — every cluster mentioning compressed sensing across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Holo-NN: New algebraic framework for private nearest neighbor search
Researchers have introduced Holo-NN, a novel algebraic framework for privacy-preserving approximate nearest neighbor (ANN) search in high-dimensional embeddings. This method replaces traditional branching operations, wh…
-
Physics-driven Ising solver accelerates computational imaging reconstruction
Researchers have developed a novel physics-driven framework for computational compressive imaging that reformulates reconstruction problems as Ising models. This approach utilizes a simulated-annealing-based Ising solve…
-
New MRI technique uses Gaussian splatting for motion estimation
Researchers have developed a novel algorithm for free-breathing abdominal MRI that simultaneously reconstructs images and estimates motion. This method, called DoReMe, represents respiratory motion using Gaussian primit…
-
New SISTA-Net method enhances single-pixel imaging with compressive sensing
Researchers have developed SISTA-Net, a novel self-supervised method for single-pixel imaging inspired by compressive sensing principles. This approach addresses limitations in existing methods by incorporating physical…
-
New deep unfolding network uses second-order optimization for compressed sensing
Researchers have introduced Newton Deep Unfolding (NDU-Net), a novel deep unfolding framework for compressed sensing (CS) reconstruction. Unlike previous methods that rely on first-order optimization, NDU-Net utilizes s…
-
New theory quantifies neural network feature superposition limits
Researchers have developed a new theoretical framework to understand feature superposition in neural networks, addressing the issue of cross-feature interference. By modeling linear accessibility as a compressed sensing…
-
New AI method designs sensing matrices for compressive sensing
Researchers have developed a novel method for constructing sensing matrices crucial for compressive sensing techniques. This approach utilizes a neural network that learns mathematical properties rather than relying on …
-
Compressed Sensing Unsuitable for LLM Inference Storage Compression
Compressed sensing is not a suitable method for compressing KV cache data during LLM inference due to the data's lack of sparsity and the need for deterministic, lossless operations. Instead, practical improvements in i…
-
New proposition links randomness and compression in deep learning models
A new proposition connects randomness and compression in machine learning models using Gibbs entropy. Researchers demonstrated that lossy compression can be viewed as a form of directed randomness that preserves informa…
-
New book "Mathematics of Data Science" published on arXiv
A new book titled "Mathematics of Data Science" has been published on arXiv, authored by Thomas Strohmer. The book delves into the mathematical underpinnings of data science, covering topics such as singular value decom…
-
New AI methods enhance MRI reconstruction and uncertainty quantification
Two new research papers propose advanced methods for magnetic resonance imaging (MRI) reconstruction. The first paper introduces a Bayesian framework utilizing sparsity priors and Markov Chain Monte Carlo sampling to im…