For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit sphere, as opposed to the entire space, and the threshold can be trained in a boun…
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.
168,694 papers · 148 categories
Trend · papers per month
48 results for “reduced parameters”
This paper describes how to convert a machine learning problem into a series of map-reduce tasks. We study logistic regression algorithm. In logistic regression algorithm, it is assumed that samples are independent and each sample is assigned a probability. Parameters are obtained by maxmizing the product of all sample…
We introduce several new black-box reductions that significantly improve the design of adaptive and parameter-free online learning algorithms by simplifying analysis, improving regret guarantees, and sometimes even improving runtime. We reduce parameter-free online learning to online exp-concave optimization, we reduce…
A new method reduces dimensionality for better likelihood-free parameter estimation.
problem Estimating parameters from data with no closed-form likelihood.
method Combines reconstruction map estimation with dimension-reduction techniques.
result The proposed method outperforms existing techniques in accuracy and efficiency.
CDEFs reduce model complexity and uncover time correlations.
problem Model complexity and data efficiency in probabilistic modeling.
method Builds on deep exponential families, ties weights for reduced parameters.
result CDEFs uncover time correlations with fewer parameters.
Sliced Inverse Regression reduces parameter space for estimating complex financial models.
problem High-dimensional parameter space in stochastic differential equations.
method Sliced Inverse Regression for dimension reduction.
result Reduced computational costs in estimating parameters.
A new method reduces complexity and uncertainty in neural networks.
problem Uncertainty quantification in complex neural networks.
method Condensed Stein Variational Gradient Descent (cSVGD) method.
result Condensed SVGD provides uncertainty quantification on parameters.
Hippo optimizes deep learning hyper-parameters by reducing redundant trials.
problem Redundant hyper-parameter trials in hyper-parameter optimization.
method Hippo breaks down hyper-parameter sequences into stages and executes them in a tree structure.
result Hippo reduces GPU-hours and training time significantly compared to existing methods.
NanoFlow reduces parameter complexity in normalizing flows.
problem Efficient parameter complexity in flow-based models.
method Single neural density estimator with flow indication embedding.
result Sublinear parameter complexity achieved.
Study examines heart and football-shaped metrics, verifying geometric structure.
problem Analyzing reducible spherical conical metrics and their geometric properties.
method Examined 1-parameter heart shape and 3-parameter football shape families, verified structure theorem, used explicit metric and geodesic calculations.
result Naturally arise from Abelian differentials of the third kind, offer new evidence for spherical geometry and complex analytic structure interaction.
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that…
Paper optimizes neural network initialization using SMT solvers.
problem Improving neural network performance through better initialization.
method Reduces initialization to SMT problem solving.
result Proposed method achieves better performance than random initialization.
We consider the problem of constructing a reduced-rank regression model whose coefficient parameter is represented as a singular value decomposition with sparse singular vectors. The traditional estimation procedure for the coefficient parameter often fails when the true rank of the parameter is high. To overcome this …
Behavioral analysis of support vector machine classifier with Gaussian kernel and imbalanced datacs.LG
Analyzes SVM classifier behavior with different parameters and data types.
problem Tuning SVM parameters for balanced and imbalanced data.
method Behavioral analysis of SVM with different parameters and data types, proposing a novel search algorithm.
result Proposed search algorithm reduces computational time and provides expected kernel function range.
We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the convolution filters. Training is performed in an interleaved fashion; some batches unde…
New method reduces over-pessimism in Bayesian control under parameter uncertainty.
problem Over-pessimism in Bayesian control due to misspecified priors.
method Distributionally robust Bayesian control (DRBC) with strong duality and optimization.
result Validated algorithm on synthetic and real data, reducing over-pessimism.
Scout-Nd optimizes parameters of stochastic simulators efficiently.
problem Optimizing parameters of stochastic, computationally expensive simulators.
method Scout-Nd algorithm, reducing gradient noise, multi-fidelity schemes.
result Demonstrates better performance compared to existing methods.
We consider partially observed multiscale diffusion models that are specified up to an unknown vector parameter. We establish for a very general class of test functions that the filter of the original model converges to a filter of reduced dimension. Then, this result is used to justify statistical estimation for the u…
Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Surveycs.LG
Survey on reducing deep neural network training complexity.
problem Efficient training of large deep neural networks.
method Pruning and freezing parts of the network during training.
result Dimensionality reduction improves training efficiency.
FedLog reduces communication in federated learning by sharing data summaries.
problem Significant communication overhead in federated learning with large model parameters.
method Shares minimal sufficient statistics via Bayesian inference and differential privacy.
result High learning accuracy with low communication overhead.
Compact DNNs increase memory footprint and reduce energy efficiency.
problem Designing compact deep neural networks (DNNs) for improved energy efficiency.
method Evaluation of recently proposed compact DNNs on a Tesla P100 GPU.
result Higher number of activations and memory footprint lead to reduced energy efficiency.
Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and…
Bayesian classification and regression with high order interactions is largely infeasible because Markov chain Monte Carlo (MCMC) would need to be applied with a great many parameters, whose number increases rapidly with the order. In this paper we show how to make it feasible by effectively reducing the number of para…
Empirical study shows removing neural parameter symmetries impacts model performance.
problem Understanding the impact of neural parameter symmetries on model performance.
method Developed two methods to reduce parameter space symmetries in neural networks.
result Removing parameter symmetries can lead to faster and more effective Bayesian neural network training.
Despite their successes in the field of self-learning AI, Convolutional Neural Networks (CNNs) suffer from having too many trainable parameters, impacting computational performance. Several approaches have been proposed to reduce the number of parameters in the visual domain, the Inception architecture [Szegedy et al.,…
Determining an appropriate number of features for each layer in a neural network is an important and difficult task. This task is especially important in applications on systems with limited memory or processing power. Many current approaches to reduce network size either utilize iterative procedures, which can extend …
New method reduces PDE model parameters by 30% with sparsity.
problem Redundant parameters in neural network projections.
method Bregman iterations for sparsity, POD compression, bias propagation.
result 30% fewer parameters with similar accuracy.
KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.
problem Expensive memory usage for training ConvNets on embedded devices.
method Kernel Modulation (KM) method that adapts all network parameters for each task.
result KM delivers up to 9% higher accuracy than other parameter-efficient methods.
Gravitational-wave data analysis is rapidly absorbing techniques from deep learning, with a focus on convolutional networks and related methods that treat noisy time series as images. We pursue an alternative approach, in which waveforms are first represented as weighted sums over reduced bases (reduced-order modeling)…
New method reduces communication in deep learning training.
problem Communication overhead in distributed deep learning training.
method Random-block sparsification to reduce gradients communicated.
result Performance close to standard SGD with reduced communication.
LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.
problem Efficiently solving time-dependent PDEs with deep neural networks.
method Low-rank constraint on network weights using SVD for efficient parameter updates.
result LR-EDNN achieves comparable accuracy to full EDNN with fewer parameters and lower cost.
This paper proposes a new method to adapt ROMs for new parameter settings.
problem ROMs lack robustness when applied to new parameter settings.
method Regression trees on Grassmann Manifold to learn the mapping between parameters and POD bases.
result The proposed method is capable of establishing the mapping between parameters and POD bases, thus adapting ROMs for new parameters.
New model reduces volatility parameters and complexity.
problem Accurately modeling multivariate volatility with network structure.
method Introduces a new multivariate volatility model using both low and high-frequency data.
result The model significantly reduces parameter count and computational complexity.
New framework reduces LLM complexity by directly finetuning in Boolean domain.
problem Reducing the complexity of large language models (LLMs) while maintaining performance.
method Proposes a novel framework using multi-kernel Boolean parameters for direct finetuning in the Boolean domain.
result Significantly reduces complexity during both finetuning and inference, outperforming recent techniques.
New algorithm reduces regret from sqrt(T) to polylog(T) in stochastic contextual linear bandits.
problem Achieving logarithmic regret in stochastic contextual linear bandits.
method Low Regret Stochastic Contextual Bandits ( exttt{LR-SCB}) algorithm, exploiting stochastic contexts and parameter estimation.
result Logarithmic regret (polylog(T)) achieved, improving over sqrt(T) lower bound.
New multigrid approach reduces CNN parameters by focusing on structured convolutions.
problem Redundancy in standard CNNs leads to high parameter count.
method Replace standard convolutions with structured multilevel convolutions.
result Linearly proportional number of parameters to network width, no loss in accuracy.
A new method reduces memory requirements for sorting high-dimensional data.
problem Efficiently sorting and organizing high-dimensional data with low memory usage.
method Iteratively shuffles N indices and applies SoftSort optimization steps.
result Significantly improves sorting quality for multidimensional data.
Adaptive multi-domain learning reduces parameter count for efficient deep learning.
problem Different domains have varying complexity, leading to inefficient model training.
method Proposes adaptive parameterization to reduce model complexity without sacrificing performance.
result Efficient multi-domain learning solutions with far fewer parameters.
Time-varying parameters are shown to be ridge regressions, simplifying computations and tuning.
problem Capturing structural change in economic data.
method Ridge regression approach, including cross-validation for tuning, and extensions for sparsity and reduced-rank restrictions.
result The method efficiently estimates large numbers of time-varying parameters, demonstrated with Canadian monetary policy data.
We develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The systematic design addresses the choice of network size and regularization of parameters. …
We consider a general framework for reducing the number of trainable model parameters in deep learning networks by decomposing linear operators as a product of sums of simpler linear operators. Recently proposed deep learning architectures such as CNN, KFC, Dilated CNN, etc. are all subsumed in this framework and we il…
Deep Fried Convnetscs.LG
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important …
Derives exact gradients for linear optics with single photons.
problem Gradient estimation for linear optics with single photons.
method Generalized parameter shift rule for linear optics.
result Derives analytical formula for gradients in linear optics.
Cost-aware SBI reduces expensive simulations in complex models.
problem High computational cost in simulating complex models.
method Combination of rejection and self-normalised importance sampling.
result Significant reduction in overall cost of inference.
This work analyzes how users and services adapt to reduce risk, leading to specialization.
problem Adaptation of users and services to reduce risk affects learning and performance.
method Analyzed a class of dynamics where users allocate participation and services update parameters.
result Repeated myopic updates with multiple learners lead to better outcomes than repeated risk minimization.
Tensor factorization has become an increasingly popular approach to knowledge graph completion(KGC), which is the task of automatically predicting missing facts in a knowledge graph. However, even with a simple model like CANDECOMP/PARAFAC(CP) tensor decomposition, KGC on existing knowledge graphs is impractical in res…
IENs reduce neural network variance without increasing complexity.
problem Reducing variance in neural networks without increasing model complexity.
method IENs use ensemble parameters during training to reduce variance, removing them during testing.
result IENs reduce network variance by a factor of , leading to significant error rate decreases.
Transformers reduce redundancy by focusing on invariant relational quantities.
problem Substantial internal redundancy in Transformer models due to coordinate-dependent representations and continuous symmetries.
method Reformulate representations, attention mechanisms, and optimization dynamics in terms of invariant relational quantities, eliminating redundant degrees of freedom by construction.
result Architectures that operate directly on relational structures, providing a principled geometric framework for reducing parameter redundancy and analyzing optimization.