In this paper, we first introduce the weighted forward reduced volume of Ricci flow. The weighted forward reduced volume, which related to expanders of Ricci flow, is well-defined on noncompact manifolds and monotone non-increasing under Ricci flow. Moreover, we show that, just the same as the Perelman's reduced volume…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “reduced weights”
This paper investigates weight-sharing in NAS, revealing its impact and providing solutions.
problem Reducing the time and computational cost of training neural networks.
method Comprehensive experiments on weight-sharing in NAS, analyzing variance and interference.
result Properly reducing weight sharing can reduce variance and improve model performance.
Diversifying an Indexq-fin.PM
A new index rebalancing strategy reduces large constituent weights without undesirable effects.
problem Undesirable effects of current Nasdaq-100 index rebalancing.
method A simple rebalancing strategy that avoids undesirable effects.
result Preserves the order of index weights and prevents maximum weight increase.
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.
Random weights in GNNs match learned weights in performance.
problem Feature rank collapse in GNNs.
method Replacing learned weights with random weights.
result Random weights achieve comparable performance to learned weights, reducing training time and memory usage.
SWAT reduces training efficiency and speed for CNNs.
problem Efficient training of neural networks on sparse hardware.
method SWAT modifies backpropagation to eliminate small weights and activations.
result SWAT reduces FLOPS by 80% on ResNet-50 for ImageNet, improving training speed by 3.3x.
Improved RTM uses integer weights to reduce computation and increase interpretability.
problem Lack of interpretability in nonlinear regression models.
method Integer weighted RTM clauses, combined with a novel learning scheme.
result Significantly reduced computation cost with improved accuracy.
WNQ uses weight normalization to reduce quantization error in deep neural networks.
problem High quantization error in deep neural networks due to long-tail distribution of weights.
method Weight normalization to avoid long-tail distribution and reduce quantization error.
result WNQ achieves state-of-the-art performance on CIFAR-100 and ImageNet.
Hierarchical IWAE reduces sample redundancy for better inference.
problem Improving variational inference by reducing sample redundancy.
method Introduces a hierarchical structure to induce correlation among proposals.
result Maximizing the lower bound implicitly minimizes variance, improving inference performance.
Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …
This work improves DNN weight quantization with ADMM, achieving lossless binarization and reduced search space.
problem Improving DNN model compression and accuracy with low bit quantization.
method Extending ADMM framework for DNN weight quantization with progressive multi-step approach.
result Achieved lossless and fully binarized DNNs with reduced accuracy loss.
PruneTrain speeds up neural network training by dynamically pruning weights.
problem Efficiently training large neural networks with high compute and memory costs.
method Structured group-lasso regularization and reconfiguration techniques to reduce weights and model size.
result Achieved 39% reduction in end-to-end training time for ResNet50 on ImageNet.
WTM reduces clause usage and computation time for pattern recognition.
problem High computation time and memory usage in Tsetlin Machine.
method Weighting clauses and using binomial sampling to reduce complexity.
result WTM achieves similar accuracy with fewer clauses and faster training.
A method to reduce memory usage in deep learning models by adding inducing weights.
problem Memory inefficiency in Bayesian neural networks and deep ensembles.
method Augmenting the weight matrix with inducing weights and using Matheron's conditional Gaussian sampling rule.
result Reduces parameter size to 24.3% of a single neural network while maintaining competitive performance.
Paper applies FloatSD8 to LSTM networks, reducing complexity and power.
problem Training and inference complexity of LSTM networks.
method Applied FloatSD8 for weights, 8-bit quantization for gradients/activations, reduced arithmetic precision.
result Successfully trained LSTM models with reduced complexity and preserved accuracy.
RSO uses random weight perturbations to train deep networks without gradients.
problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.
Randomly chosen primary hidden units and derived secondary units reduce neural network complexity.
problem Large number of hidden units in neural networks.
method Introducing primary and secondary hidden units with random weights for primary units and derived weights for secondary units.
result Significant reduction in the number of hidden units without compromising accuracy.
We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision post-training produces classification accuracies within 2% of floating point networks…
New method reduces model bias and variance by adjusting training sample weights based on label uncertainty.
problem Tradeoff between model bias and variance in classification models.
method Estimate label uncertainty, adjust training sample weights, and fine-tune decision boundary.
result Improves model performance and reduces variance in physical activity recognition.
LCW reduces activation shift in neural networks, improving training efficiency and generalization.
problem Activation shift in neural networks leading to non-zero mean preactivation values.
method Linearly constrained weights (LCW) to reduce activation shift in fully connected and convolutional layers.
result LCW resolves the vanishing gradient problem and improves generalization of neural networks.
A new weighted dissimilarity measure reduces positioning errors in feature-based systems.
problem Reducing errors in feature-based positioning systems, especially in areas with high variability.
method Iterative scheme using location-dependent standard deviations as weights.
result Maximum radial positioning error reduced by 40% using the weighted dissimilarity measure.
K-FAC speeds up training of modern neural networks with linear weight-sharing.
problem Efficiently training modern neural networks with linear weight-sharing layers.
method Kronecker-Factored Approximate Curvature (K-FAC) applied to linear weight-sharing layers.
result K-FAC-reduce is generally faster than K-FAC-expand for deep linear networks.
Signed network models reduce portfolio risk by considering negative edges in financial markets.
problem Tackles portfolio optimization in financial markets by exploiting negative edges in network representations.
method Proposes a discrete optimization scheme to reduce asset selection, building time series of signed networks from asset returns.
result Empirical results show that signed network portfolios perform similarly to classical mean-variance optimization and equally weighted benchmarks.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
We propose an algorithm for deciding whether a given braid is pseudo-Anosov, reducible, or periodic. The algorithm is based on Garside's weighted decomposition and is polynomial-time in the word-length of an input braid. Moreover, a reduction system of circles can be found completely if the input is a certain type of r…
FairWASP optimizes training data to reduce disparities across subgroups.
problem Reducing disparities in model outputs across different subgroups in machine learning.
method A novel pre-processing approach that minimizes Wasserstein distance to the original dataset while satisfying demographic parity.
result Integer weights are optimal, allowing FairWASP to be understood as duplicating or eliminating samples.
DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.
problem Reducing computational overhead and ambiguity in convolutional neural networks.
method Introducing a primal learning problem and constructing a dual convex training program, using Fenchel conjugates and Karush-Kuhn-Tucker conditions.
result Eliminates ambiguity and reduces computational overhead in constructing a large kernel matrix.
A new method reduces the computational cost of KernelSHAP for explaining predictions.
problem Efficiently approximating Shapley values for complex models with many features.
method Replacing stochastic weights with deterministic ones in KernelSHAP.
result Reduces the number of contribution function evaluations by 5% to 50%.
Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural networks because smaller memory footprint is crucial not only for reducing storage re…
One reflection suffices for orthogonal weights, reducing GPU usage.
problem Efficiently computing orthogonal weight matrices without high GPU utilization.
method Use an auxiliary neural network to compute one reflection instead of many.
result One reflection is sufficient for orthogonal weights, improving GPU utilization.
Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested along with different inference implementation characteristics. Adopting model com…
New method reduces computational cost for Bayesian inference.
problem High computational cost in Bayesian inference.
method Coreset MCMC, a Markov chain targeting coreset posterior.
result Coreset MCMC provides higher quality posterior approximations and reduced computational cost.
Paper proposes new pruning techniques to significantly reduce DNN weights and improve model compression.
problem High computation and memory storage challenges in deep learning networks.
method Combines filter and column pruning with ADMM algorithm and introduces Network Purification and Unused Path Removal (P-RM) for post-processing.
result Achieved up to 60x compression on ResNet-18 CIFAR-10, demonstrating effectiveness of proposed methods.
TWM doesn't reduce delta in PDLPs, proving impossibility.
problem TWM in PDLPs doesn't uniformly reduce portfolio delta.
method Proved TWM's condition is self-contradictory and showed impossibility.
result No TWM can uniformly reduce portfolio delta.
Quantized Adam reduces communication cost in deep learning training.
problem Reducing communication cost in distributed deep learning training.
method Gradient and weight quantization with error feedback in Adam.
result Proposed methods converge to first-order stationary points.
A hybrid model reduces graph complexity for improved classification accuracy.
problem High computational complexity and large number of parameters in higher-order graph convolutional networks.
method Weight sharing mechanism and novel fusion pooling layer to reduce parameters and complexity.
result The proposed model achieves highest classification accuracy with fewer trainable parameters.
Introduces directed diagrammatic reducibility with group and topological implications.
problem Diagrammatic reducibility in relative presentations.
method Adapting classical tools for diagrammatic reducibility to directed diagrammatic reducibility.
result Strong group theoretic and topological consequences of directed diagrammatic reducibility.
New invariants help solve existence of weighted cscK metrics.
problem Existence of weighted cscK metrics in K-stability.
method Introduced weighted analytic delta invariant and beta invariant.
result Sufficient condition for existence of weighted cscK metrics.
Extremal Kahler metrics and Sasaki-Einstein metrics characterized via coercive energy.
problem Characterizing extremal Kahler and Sasaki metrics using energy coercivity.
method Maximal complex torus, coercive weighted Mabuchi energy, K-polystability.
result Coercive weighted Mabuchi energy implies strict positivity of Donaldson-Futaki invariant and existence of extremal metrics.
Dr. of Crosswise reduces over-parametrization in neural networks.
problem Reduction of over-parametrization in neural networks.
method Introduces a new operand for rapid computation in neural networks framework.
result Reduces over-parametrization in neural networks.
New CV method reduces bias in spatial prediction models.
problem Bias in standard cross-validation due to uneven sampling.
method Target-Weighted Cross-Validation (TWCV) framework.
result Weighted CV approaches reduce bias in prediction error.
Proposes robust graph embedding with noisy link weights.
problem Learning feature vectors from noisy link weights.
method β-graph embedding with empirical moment β-score.
result Computational tractability and local minimization of β-score.
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.
We introduce a notion of a Kähler metric with constant weighted scalar curvature on a compact Kähler manifold , depending on a fixed real torus in the reduced group of automorphisms of , and two smooth (weight) functions and , defined on the momentum image (with respect to …
In portfolio analysis, the traditional approach of replacing population moments with sample counterparts may lead to suboptimal portfolio choices. I show that optimal portfolio weights can be estimated using a machine learning (ML) framework, where the outcome to be predicted is a constant and the vector of explanatory…
Study improves epidemic forecasting with a sparsified GSRNN.
problem Epidemic forecasting on real-world health data.
method Graph-structured recurrent neural network (GSRNN) with sparsification via transformed- penalty.
result Maintained prediction accuracy with 70% of network weights being zero.
AutoQ automatically optimizes quantization for CNNs, reducing latency and energy.
problem Efficiently quantizing CNN weights for low-power mobile devices.
method Hierarchical-DRL for kernel-wise quantization bitwidth selection.
result Reduces inference latency and energy consumption by 54.06% and 50.69% respectively.
A new RNN architecture reduces model size and improves performance.
problem Overparameterization and resource limitations in RNNs.
method Jointly encodes weight matrices using tensor-train factorization.
result Reduces model size by several orders of magnitude without sacrificing performance.