New GPU algorithm boosts machine learning with larger datasets.
problem Limited GPU memory restricts training data size.
method Out-of-core GPU gradient boosting algorithm.
result Training larger datasets on GPUs without accuracy loss.
On-device research index
arXiv research
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.
168,932 papers · 148 categories
Trend · papers per month
36 results for “memory-limited”
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.
problem Catastrophic forgetting and memory limitations in continual learning.
method Trains autoencoders with Neural Style Transfer to encode images, replay encoded episodes to avoid forgetting, and use centroids and covariance matrices for pseudo-images when memory is full.
result Increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.
Federated PCA algorithm uses limited memory and privacy-preserving techniques.
problem Memory-limited federated PCA in an asynchronous setting.
method Incremental streaming updates, differential privacy via input-perturbation, invariant to data permutations.
result Guarantees differential privacy and robustness against stragglers.
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.
problem Adversarial bandit problem with limited memory storage.
method Hierarchical learning policy with sublinear memory requirement.
result Established sublinear regret bounds for weak and shifting regrets.
The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network ou…
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 …
Memory-efficient learning for large-scale imaging systems.
problem Memory limitations in GPUs for real-world large-scale inverse problems.
method Exploits reversibility of network layers to enable data-driven design.
result Demonstrated on small-scale and large-scale real-world systems.
Survey on statistical inference under memory constraints.
problem Effect of memory limitations on statistical inference performance.
method Review of state-of-the-art in several canonical problems.
result Identification of fundamental building blocks and useful techniques.
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.
problem Covariate shift in nonparametric regression.
method Random projections in RKHS to reduce computational demands.
result Significant computational savings can be achieved without compromising learning performance 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.
problem Hardware limitations restrict the size of ensembles and network capacity, degrading performance.
method Packed-Ensembles (PE) design and train lightweight structured ensembles by modulating encoding space and parallelizing into a single backbone.
result PE accurately preserves diversity and maintains performance on key metrics like accuracy, calibration, and out-of-distribution detection.
Study on deleting user data in linear regression models to maintain limited memory.
problem Deleting user data in a limited time frame for statistical models.
method Proposed FIFD-OLS and FIFD-Adaptive Ridge algorithms for low-dimensional and online settings.
result Demonstrated effectiveness of FIFD-Adaptive Ridge in maintaining statistical efficiency.
Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Networkeess.AS
Paper proposes low-rank gradient approximation to save memory for deep neural network training.
problem Memory limitation on mobile devices for deep neural network training.
method Approximating gradient matrices using low-rank parameterization.
result Reduces training memory by about 33.0% for Adam optimization and 4.5% relative lower word error rate on ASR personalization task.
New fair PCA method using streaming algorithms with statistical guarantees.
problem Perform PCA while ensuring fair projected distributions.
method Formulated new notion PAFO learnability, proposed fair noisy power method (FNPM) for memory efficiency.
result First statistical guarantee for fair PCA in streaming setting.
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.
problem Memory constraints limit the scalability of memory-intensive machine learning algorithms.
method Developed an XLA compiler extension that adjusts algorithm data-flow representation to fit memory limits.
result k-nearest neighbour and sparse Gaussian process regression can be run at larger scales.
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 …
New method for option pricing using Monte Carlo and least squares.
problem Computing European option prices in high dimensions.
method Combines Monte Carlo simulation with least squares approximation and randomized Kaczmarz algorithm.
result Efficient method for high-dimensional integration and option pricing.
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…
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…
Reservoir computers and RNNs fall short of optimal prediction for stochastic PDFA.
problem Predicting stochastic processes generated by probabilistic deterministic finite-state automata.
method Generalized linear models, Reservoir computers, and Long Short-Term Memory (LSTM) RNNs were tested.
result Each method can fall short of maximal predictive accuracy by up to 50% after training.
Mini-batch sub-sampling in neural network training is unavoidable, due to growing data demands, memory-limited computational resources such as graphical processing units (GPUs), and the dynamics of on-line learning. In this study we specifically distinguish between static mini-batch sub-sampled loss functions, where mi…
CoHiRF extends clustering methods to handle high-dimensional data efficiently.
problem Scalability limits of existing clustering methods.
method Hierarchical consensus framework operating on label assignments.
result Improves robustness and scalability to high-dimensional noise.
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle this issue. The most prominent algorithm in this line of research is LARS, which by employing layerwise adaptive learning ra…
Quantum memory limits set by relativity theory.
problem Quantum memory efficiency and relativity constraints.
method Relativistic quantum field theory and Lieb-Robinson bounds.
result Quantum memory capacity is limited by fundamental physics.
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.
problem Catastrophic forgetting in class-incremental learning.
method Memory-efficient exemplar preserving scheme and domain-compatible feature extractors.
result Low-fidelity exemplar samples can replace high-fidelity ones with less memory cost.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.
Two novel search strategies reduce complexity for target localization with size-dependent noise.
problem Target localization with varying measurement noise based on query region size.
method Proposes and strategies with low complexity and connected query geometry.
result Unified analysis shows asymptotically optimal in search time, near-optimal in rate.
Paper compresses ViTs models by 60% with minimal accuracy loss.
problem Memory constraints in ViTs models.
method Activation-aware low-rank tensor approximations.
result 60% reduction in model size with <1% 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…
Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Gamescs.LG
Algorithm improves RL model selection for repeated games with utility maximization.
problem Optimal policy learning in repeated games with unknown opponent strategy.
method Proposes MRBEAR for average reward RL, applying to utility maximization in repeated games.
result Regret bound shows linear dependence on number of model classes in average reward RL.