A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
BDC compresses both sample size and dimensionality of large datasets.
We give first examples of finitely generated groups having an intermediate, with values in (0,1), Hilbert space compression (which is a numerical parameter measuring the distortion required to embed a metric space into Hilbert space). These groups include certain diagram groups. In particular, we show that the Hilbert …
OptiNet achieves near-minimax error rates with compression in Euclidean space.
It was proved in 1998 by Ben-David and Litman that a concept space has a sample compression scheme of size d if and only if every finite subspace has a sample compression scheme of size d. In the compactness theorem, measurability of the hypotheses of the created sample compression scheme is not guaranteed; at the same…
CSDM integrates compressed sensing into diffusion models for faster data generation.
Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore specialized areas for exploration and design of large spaces in terms of size, spe…
New method compresses facial videos using GANs and latent space optimization.
This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-constrained platforms. Modern DNN compression techniques comprise various hyperparameters that require per-layer customization to ensure high ac…
Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a generative model. We search and constrain on latent variable space to make the m…
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned probability model, which is used to impose an entropy penalty on the parameter r…
If one tries to embed a metric space uniformly in Hilbert space, how close to quasi-isometric could the embedding be? We answer this question for finite dimensional CAT(0) cube complexes and for hyperbolic groups. In particular, we show that the Hilbert space compression of any hyperbolic group is 1.
New method connects compression bodies through cone manifolds.
Galen algorithm compresses neural networks for specific hardware with reduced latency.
The paper uses information geometry to analyze model compression techniques, focusing on operator factorization.
HOPE uses Hilbert space to deconstruct deep network representations.
Generalizes bits back coding for time-series models with latent Markov structures.
Reduces multiclass and regression compression schemes to binary ones.
Proposes using equivariant generative models for compressed sensing with unknown orientations.
In this paper we prove that one can find surgeries arbitrarily close to infinity in the Dehn surgery space of the figure eight knot complement for which some immersed totally geodesic surface compresses.
Detects handlebodies and mapping class extensions using bordered Floer homology.
Unified bounds linking compressibility, fractal dimensions, and mutual information.
Reduces policy space complexity for reinforcement learning.
We present a new similarity measure based on information theoretic measures which is superior than Normalized Compression Distance for clustering problems and inherits the useful properties of conditional Kolmogorov complexity. We show that Normalized Compression Dictionary Size and Normalized Compression Dictionary En…
Investigates principles of generalization in list learning, refutes sample compression conjecture.
Paper proposes compressive ICA algorithms for ICA model.
This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.
This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.
In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior are trained jointly to minimize a rate-distortion loss, which is closely relate…
We initiate the rigorous study of classification in quasi-metric spaces. These are point sets endowed with a distance function that is non-negative and also satisfies the triangle inequality, but is asymmetric. We develop and refine a learning algorithm for quasi-metrics based on sample compression and nearest neighbor…
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank…
In this paper, we consider linear state-space models with compressible innovations and convergent transition matrices in order to model spatiotemporally sparse transient events. We perform parameter and state estimation using a dynamic compressed sensing framework and develop an efficient solution consisting of two nes…
This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.
The paper analyzes geometric densities and compression radii for knot types.
End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer compression ratios when applied to a state-of-the-art attention based end-to-end ASR mod…
We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size. This quantity is defined as the size of the smallest subset of the training data that induces the same version space. We show various a…
We show that the type function of a space with finite asymptotic dimension estimates its Hilbert (or any ) compression. The method allows to obtain the lower bound of the compression of the lamplighter group , which has infinite asymptotic dimension.
Bayesian Attention Networks compress data by focusing on key training samples.
Compress++ speeds up distribution compression to near-linear time.
A CAE improves DNN's outlier and adversary defense.
The paper defines and studies discrete p-density and compression-radius profiles of lattice knots.
GeneCAI optimizes DNN compression hyper-parameters for mobile devices.
Given Poincare spaces M and X, we study the possibility of compressing embeddings of M x I in X x I down to embeddings of M in X. This results in a new approach to embedding in the metastable range both in the smooth and Poincare duality categories.
Paper presents J-RFDL for robust DL in compressed space, improving data representation robustness and accuracy.
Given a 3-manifold that can be written as the double of a compression body, we compute the Chern-Simons critical values for arbitrary compact connected structure groups. We also show that the moduli space of flat connections is connected when there are no reducibles.
Unified SVD compression fails in practical tasks, highlighting the importance of per layer activation reconstruction.
A novel method compresses point cloud attributes by folding them onto a 2D grid.
EAST compresses deep ConvNets for tiny memory nodes.
The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for l…