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.
A new method sparsifies neural networks by reducing sensitive parameters to zero.
New GPU algorithm boosts machine learning with larger datasets.
In this paper, we propose an acceleration scheme for online memory-limited PCA methods. Our scheme converges to the first eigenvectors in a single data pass. We provide empirical convergence results of our scheme based on the spiked covariance model. Our scheme does not require any predefined parameters such as t…
In this paper, we consider the streaming memory-limited matrix completion problem when the observed entries are noisy versions of a small random fraction of the original entries. We are interested in scenarios where the matrix size is very large so the matrix is very hard to store and manipulate. Here, columns of the o…
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
Federated PCA algorithm uses limited memory and privacy-preserving techniques.
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: the local quadratic model, the identification of a descent direction, and the Wolfe …
Memory-limited learning tackles adversarial bandits with reduced storage.
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a …
New method for option pricing using Monte Carlo and least squares.
Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by operations on the weight matrices describing the DNN. As DNNs incorporate more layers a…
Memory-efficient learning for large-scale imaging systems.
Solving l1 regularized optimization problems is common in the fields of computational biology, signal processing and machine learning. Such l1 regularization is utilized to find sparse minimizers of convex functions. A well-known example is the LASSO problem, where the l1 norm regularizes a quadratic function. A multil…
Sparse neural networks can improve performance with less memory.
Survey on statistical inference under memory constraints.
CoHiRF extends clustering methods to handle high-dimensional data efficiently.
Two novel search strategies reduce complexity for target localization with size-dependent noise.
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables memory-limited execution of several statistical analyses over streams, including online featu…
This paper improves computational efficiency in kernel ridge regression under covariate shift.
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpfu…
Packed-Ensembles improve uncertainty estimation in constrained hardware.
Study on deleting user data in linear regression models to maintain limited memory.
Quantum memory limits set by relativity theory.
Paper proposes low-rank gradient approximation to save memory for deep neural network training.
New fair PCA method using streaming algorithms with statistical guarantees.
While accelerators such as GPUs have limited memory, deep neural networks are becoming larger and will not fit with the memory limitation of accelerators for training. We propose an approach to tackle this problem by rewriting the computational graph of a neural network, in which swap-out and swap-in operations are ins…
XLA compiler extension improves memory efficiency for machine learning.
Penalized regression models such as the lasso have been extensively applied to analyzing high-dimensional data sets. However, due to memory limitations, existing R packages like glmnet and ncvreg are not capable of fitting lasso-type models for ultrahigh-dimensional, multi-gigabyte data sets that are increasingly seen …
Algorithm improves RL model selection for repeated games with utility maximization.
Reservoir computers and RNNs fall short of optimal prediction for stochastic PDFA.
We consider streaming, one-pass principal component analysis (PCA), in the high-dimensional regime, with limited memory. Here, -dimensional samples are presented sequentially, and the goal is to produce the -dimensional subspace that best approximates these points. Standard algorithms require memory; mea…
Efficiently preserves old class knowledge in memory-limited settings.
New LAMB optimizer reduces BERT training time from 3 days to 76 minutes.
This study addresses the challenges of dynamic mini-batch sub-sampling in neural network training.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
Paper compresses ViTs models by 60% with minimal accuracy loss.
Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors. It is often the case that a node is not only influenc…
Higgs bundles used in new applications.
Android and Facebook provide third-party applications with access to users' private data and the ability to perform potentially sensitive operations (e.g., post to a user's wall or place phone calls). As a security measure, these platforms restrict applications' privileges with permission systems: users must approve th…
Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing applications into deep learning architectures. Using this approach, we estimate each application's functionality with an estimator, which is impl…
New methods improve autotuning of exascale applications by 1.5x.
Curved flats linked to pairs of Lie applicable surfaces.
DeepPlace learns to place applications in clusters using RL.
Interactive applications incorporating high-data rate sensing and computer vision are becoming possible due to novel runtime systems and the use of parallel computation resources. To allow interactive use, such applications require careful tuning of multiple application parameters to meet required fidelity and latency …
An overview of some of the recent developments in the theory of valuations on convex sets and its generalizations to manifolds is given. The exposition is focused towards applications to integral geometry; several of such applications are discussed.
The aim of this paper is to discuss some applications of general topology in computer algorithms including modeling and simulation, and also in computer graphics and image processing. While the progress in these areas heavily depends on advances in computing hardware, the major intellectual achievements are the algorit…
Survey of deep RL in intelligent transportation systems.
Adjustment reduces bias in widely applicable Bayesian information criterion.