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.
Improves convergence speed in compressive sensing with a new probabilistic approach.
In many compressive sensing problems today, the relationship between the measurements and the unknowns could be nonlinear. Traditional treatment of such nonlinear relationships have been to approximate the nonlinearity via a linear model and the subsequent un-modeled dynamics as noise. The ability to more accurately ch…
Paper develops a framework to protect data privacy using compressive adversarial methods.
The recent framework of compressive statistical learning aims at designing tractable learning algorithms that use only a heavily compressed representation-or sketch-of massive datasets. Compressive K-Means (CKM) is such a method: it estimates the centroids of data clusters from pooled, non-linear, random signatures of …
We develop embeddings for nonlinear subspaces preserving vector norms.
This paper introduces a new measure to identify model redundancy in compressed CNNs.
We simplify complex regression coefficients using linearization and feature comparison.
We describe a general framework -- compressive statistical learning -- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A…
New measure LMN explains neural network grokking.
Recurrent iterated function systems (RIFSs) are improvements of iterated function systems (IFSs) using elements of the theory of Marcovian stochastic processes which can produce more natural looking images. We construct new RIFSs consisting substantially of a vertical contraction factor function and nonlinear transform…
This paper compresses large datasets for efficient machine learning.
Compressed imitation learning uses simplicity priors for efficient expert behavior copying.
Unified method learns latent spaces from labeled data.
As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression metho…
Efficiently compress overparameterized deep models by focusing on low-dimensional learning dynamics.
Draft proposes adapting neural networks to match naive Bayes classifiers.
We consider the problem of reconstructing signals and images from periodic nonlinearities. For such problems, we design a measurement scheme that supports efficient reconstruction; moreover, our method can be adapted to extend to compressive sensing-based signal and image acquisition systems. Our techniques can be pote…
We consider maps between Riemannian manifolds in which the map is a stationary point of the nonlinear Hodge energy. The variational equations of this functional form a quasilinear, nondiagonal, nonuniformly elliptic system which models certain kinds of compressible flow. Conditions are found under which singular sets o…
Autoencoders fail to capture sparse structure in 1-bit data compression.
FastDeepIoT optimizes neural network execution time on mobile devices.
Unified framework for uniform signal recovery in nonlinear GCS with 1-bit/quantized measurements.
New bounds show large language models can generalize beyond training data.
We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds to hierarchical nonlinear tensor decomposition. We propose to solve the learning…
We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements. The signals are assumed sparse, with unknown support, and evolve over time according to a generic nonlinear dynamical model. Our algorithm, based on recent theoretical results for -$…
In this era of data deluge, many signal processing and machine learning tasks are faced with high-dimensional datasets, including images, videos, as well as time series generated from social, commercial and brain network interactions. Their efficient processing calls for dimensionality reduction techniques capable of p…
Bayesian data sketching speeds up inference for large functional data.
Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which individual features are most salient. While recent work from our group and others has demonstrated the utility of time-lagged co-variate models to study such …
A novel deep learning method for real-time EEG signal compression.
We develop an explicit and tractable representation of a twist-grain-boundary phase of a smectic A liquid crystal. This allows us to calculate the interaction energy between grain boundaries and the relative contributions from the bending and compression deformations. We discuss the special stability of the 90 degree g…
New method reduces PDE model parameters by 30% with sparsity.
New methods improve tree ensemble models by compressing them while maintaining accuracy.
This paper simplifies deep learning networks by mapping them to a linear function of a feature map.
Paper proves stability of multi-dimensional rarefaction waves in gas dynamics.
Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model size and the intensive computation. To address this issue, various approximatio…
The paper proposes a least squares method for binary compressive sampling with low intrinsic dimension signals.
The paper compares traditional regression with modern neural network methods for financial hedging and risk compression.
Improved neural network training for speech recognition using power-law nonlinearity and uniform distribution criterion.
The Minimum Description Length (MDL) principle states that the optimal model for a given data set is that which compresses it best. Due to practial limitations the model can be restricted to a class such as linear regression models, which we address in this study. As in other formulations such as the LASSO and forward …
Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated neural networks that achieve state of the art performance on gradient based adv…
Develops an online Gaussian process method that maintains convergence guarantees without sample complexity issues.
Information bottleneck (IB) is a technique for extracting information in one random variable that is relevant for predicting another random variable . IB works by encoding in a compressed "bottleneck" random variable from which can be accurately decoded. However, finding the optimal bottleneck variab…
New tensor network decompositions improve CNN performance.
Generalization in nonlinear least squares can be studied via algorithmic stability and effective dimension.
In this paper, we develop a new framework for sensing and recovering structured signals. In contrast to compressive sensing (CS) systems that employ linear measurements, sparse representations, and computationally complex convex/greedy algorithms, we introduce a deep learning framework that supports both linear and mil…
Constraint-aware neural networks improve accuracy in fluid flow simulations.
Proposes FunNoL for better curve classification and reconstruction in multivariate functional data.
Over the past few years, we developed a mathematically rigorous method to study the dynamical processes associated to nonlinear Forchheimer flows for slightly compressible fluids. We have proved the existence of a geometric transformation which relates constant mean curvature surfaces and time-invariant pressure distri…
Deep neural networks can approximate rough functions with high accuracy.