Sparse sub-networks win transfer learning tasks.
problem Transfer learning with deep networks.
method Unstructured magnitude pruning to find winning tickets.
result Sparse sub-networks achieve similar or better accuracy than original networks.
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “sparse sub-networks”
Study finds differences in LTs across tasks and architectures, proposing a consensus-based method for generating refined lottery tickets.
problem Understanding the variability and uniqueness of Lottery Tickets across different image classification tasks and architectures.
method 28 combinations of image classification tasks and architectures, iterative pruning techniques, consensus-based method for generating refined lottery tickets.
result Disproves the uniqueness of Lottery Tickets and connects emergent mask structure to the choice of pruning.
New methods improve Laplace approximations for deep neural networks by selecting key parameters.
problem Improving uncertainty quantification in deep neural networks using computationally feasible approximations.
method Gradient-Laplace and Greedy-Laplace methods for selecting parameters in sub-network Laplace approximations.
result Gradient-Laplace method outperforms existing heuristic approaches and provides formal optimality guarantees.
Boosts share routing for multi-task learning with flexible sparse connections.
problem Designing suitable sharing mechanisms among multiple tasks in multi-task learning.
method Proposes MTNAS framework to modularize sharing into sub-networks with sparse connections and gating.
result Demonstrates consistent improvement over single-task and typical multi-task methods while maintaining efficiency.
FedDST trains sparse sub-networks to improve efficiency in federated learning.
problem Efficiently train large models on resource-limited edge devices with limited network bandwidth.
method Dynamic sparse training to reduce model size and communication.
result FedDST outperforms existing methods in federated learning, especially in non-i.i.d. settings.
We find faster-converging sub-networks that significantly reduce adversarial training time.
problem Finding optimal sub-networks for adversarial training is costly and time-consuming.
method We identify a subset of sub-networks that converge faster during training.
result Sub-networks can reduce adversarial training time by up to 49%.
Early neural network training reveals important sub-networks and weight distributions.
problem Understanding the early phases of neural network training.
method Extensive measurements and quantitative probing of weight distribution and dataset reliance.
result Deep networks are not robust to reinitializing with random weights while maintaining signs, and weight distributions are highly non-independent.
The lottery ticket hypothesis finds multiple winning sub-networks in neural networks.
problem Finding a single winning sub-network in neural networks.
method Analyzing neural networks trained in isolation and on different tasks.
result Neural networks contain multiple sub-networks that match the accuracy of the original network, not just one.
SDQL uses modular deep Q networks to efficiently learn multi-stage optimal control tasks.
problem Training complex deep reinforcement learning models for multi-stage control tasks is inefficient and unstable.
method Stacked Deep Q Learning (SDQL) with modular Q networks and backward training.
result SDQL efficiently learns optimal control policies for multi-stage tasks with high-dimensional state and action spaces.
Simplifies neural regression by combining two sub-networks for predictions and uncertainties.
problem Neural networks underestimate uncertainty, leading to overly confident predictions.
method Extends IRLS to a two-sub-network approach with shared representations and complementary loss functions.
result Proposed network is simpler to implement and more robust to uncertainty variations.
The pioneer deep neural networks (DNNs) have emerged to be deeper or wider for improving their accuracy in various applications of artificial intelligence. However, DNNs are often too heavy to deploy in practice, and it is often required to control their architectures dynamically given computing resource budget, i.e., …
This work introduces a method to compare sparse neural network topologies using graph theory.
problem Comparing and understanding sparse neural network topologies, especially during training.
method Introducing Neural Network Sparse Topology Distance (NNSTD) to measure distances between different sparse neural networks.
result Sparse neural networks can outperform over-parameterized models without further structure optimization.
AlphaNet improves supernets training with alpha-divergence.
problem Improving the uncertainty distillation in weight-sharing NAS.
method Proposes alpha-divergence for better uncertainty distillation in supernets.
result Significant improvements in model performance across various FLOPs regimes.
New method finds efficient sparse neural networks.
problem Finding efficient, sparse deep neural network models.
method Continuous Sparsification, approximating regularization.
result Surpasses state-of-the-art for pruning and ticket search.
This paper considers a Bayesian view for estimating a sub-network in a Markov random field. The sub-network corresponds to the Markov blanket of a set of query variables, where the set of potential neighbours here is big. We factorize the posterior such that the Markov blanket is conditionally independent of the networ…
DC-NAS improves neural architecture search by clustering and evaluating sub-networks.
problem Inaccurate evaluation of neural architectures in large search spaces.
method Divide-and-Conquer approach: feature representation, clustering, and evaluation of clusters.
result Achieved 75.1% top-1 accuracy on ImageNet, surpassing state-of-the-art methods.
The paper analyzes the role of ReLU gates in deep learning networks.
problem Understanding the role of gates in deep learning networks.
method Developed neural path features (NPF) and neural path values (NPV) to characterize the active sub-networks during training.
result The neural path kernel associated with NPFs is a fundamental quantity that characterizes the information stored in the gates of a DNN.
The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically increasing model capacity without a proportional increase in computation. In practice…
A distributed SGD method for heterogeneous networks with hubs and workers.
problem Learning in heterogeneous multi-level networks with worker heterogeneity and varying communication.
method Multi-Level Local SGD: distributed SGD with hub-and-spoke paradigm and hub averaging.
result The method converges with error dependent on worker heterogeneity, hub network topology, and iterations.
i-SpaSP prunes neural networks by identifying important groups of parameters, improving pruning efficiency.
problem Pruning neural networks to reduce computational cost and improve performance.
method i-SpaSP uses sparse signal recovery principles to iteratively identify and threshold important parameter groups.
result i-SpaSP achieves strong empirical results and theoretical convergence guarantees, improving pruning efficiency.
Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsitystat.ML
SNAM improves NAM's accuracy and feature selection via group sparsity.
problem Improving interpretability and accuracy in deep learning models.
method Employing group sparsity regularization in neural additive models (SNAM).
result SNAM provably converges to zero training loss and achieves exact support recovery.
Lottery tickets find good initializations for IMP with sparse training.
problem Finding good initializations for iterative magnitude pruning (IMP) in sparse networks.
method Empirical study of IMP performance with varying pre-training data and iterations.
result Training on a small fraction of data suffices to obtain good initializations for IMP.
Pruning FCNs reveals sub-networks that match CNNs' performance.
problem Understanding the inductive bias of pruning in neural networks.
method Iterative magnitude pruning of a simple FCN followed by analysis of the resulting architecture.
result Pruned FCNs exhibit key features of CNNs, suggesting new architectural biases.
Adapts CNN for robust medical image segmentation across different scanners and protocols.
problem Performance degradation of CNNs in medical image segmentation due to mismatch between training and test images.
method Designs a segmentation CNN as a concatenation of a shallow normalization CNN and a deep CNN. At test time, adapts the normalization sub-network for each test image using a denoising autoencoder.
result Consistently improves performance on multi-center MRI datasets of brain, heart, and prostate.
Study reveals trade dynamics in dry bulk shipping networks, highlighting their randomness and periodic changes.
problem Understanding the randomness and periodic changes in dry bulk shipping networks.
method Analysis of micro-level trade flow data from 2015 to 2023, focusing on grain, coal, and iron ore networks.
result Dry bulk shipping networks exhibit small-world phenomena and periodic life cycles, influenced by importing ports and global events.
This paper uses graph convolutional networks to improve the accuracy of neural architecture search.
problem Improving the precision of sampled sub-networks in weight-sharing NAS.
method Training a graph convolutional network to fit the performance of sampled sub-networks.
result Achieved higher rank correlation coefficient and better final architecture performance.
iGNN tackles inverse graph prediction using invertible neural networks.
problem Inverse graph prediction problem in data analysis and machine learning.
method Developed invertible graph neural network (iGNN) to solve inverse prediction problem on graphs.
result iGNN model allows efficient generation from output labels and forward prediction.
Bayesian principles improve neural additive models for better feature selection and uncertainty.
problem Lack of calibrated uncertainties and feature selection in neural additive models.
method Augmenting NAMs with Bayesian principles to provide credible intervals, feature selection, and interaction ranking.
result Improved performance on tabular datasets and real-world medical tasks.
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at r…
A new method clusters subjects based on brain networks without vectorizing fMRI data.
problem Distortion of clustering results when simplifying fMRI data structure.
method Wishart mixture models for multiple-view clustering of brain networks.
result Identifies multiple underlying pairs of associations between subject clusters and brain sub-networks.
Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity they are participating in within a particular time point (microlevel structure, within threads). This sub-network structure is implicit in m…
Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans. However, the size of a nodule is very diverse and can range anywhere between 3 and 30 millimeters. The high variation of nodule sizes makes classifying them a difficult and cha…
A new training method improves stability and generalization of DeepONets.
problem Training deep operator networks (DeepONets) is challenging due to nonconvex and nonlinear nature.
method Two-step training method: first train trunk network, then branch network. Introduced Gram-Schmidt orthonormalization.
result Generalization error estimate and numerical examples demonstrating effectiveness.
A model explains credit assignment in deep learning networks.
problem Understanding how deep learning assigns credit to parameters.
method Mean-field learning model with ensembles of sub-networks.
result Synaptic connections can be categorized into three types.
Paper presents a DRL framework for detecting and anticipating financial crises.
problem Detecting and adapting to financial crises using deep reinforcement learning.
method Two sub-networks, one for past performances and standard deviations, the other for contextual features. Adversarial training for robustness.
result Framework substantially outperforms traditional methods in detecting and anticipating crises.
Paper stabilizes DARTS algorithm for better neural architecture search.
problem Weak stability of DARTS algorithm leading to unreliable results.
method Amended gradient estimation method to bridge optimization gap.
result Significant improvement in search stability and larger search spaces explored.
This paper shows RBMs can maintain strong performance even after extreme pruning, but only if done early in training.
problem The computational and environmental costs of large neural networks.
method Investigating the performance of RBMs under extreme pruning conditions, inspired by the Lottery Ticket Hypothesis.
result RBMs can achieve high-quality generative performance even after 80% pruning, but performance degrades sharply above a critical point.
This work proposes splitting deep neural networks into smaller sub-networks for faster and more efficient distillation.
problem Challenges in training deep neural networks, including local optima, gradient issues, and computational demands.
method Proposes a non-end-to-end distillation approach by splitting networks into smaller, independent sub-networks (neighbourhoods).
result Independent training of smaller sub-networks can speed up distillation and improve efficiency in various applications.
Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learningstat.ML
Efficiently builds diverse sub-model ensembles for robust self-supervised learning.
problem Challenges in diversity and efficiency of deep ensembles for self-supervised representation learning.
method Ensemble of independent sub-networks with a new loss function for diversity.
result Significantly improves prediction reliability and model calibration.
ATSDLN adapts to time series data for anomaly detection.
problem Challenges in selecting and optimizing anomaly detectors for time series data.
method Adaptive Time Series Detector Learning Network (ATSDLN) that selects and optimizes detectors and parameters.
result ATSDLN outperforms other methods in anomaly detection across various datasets.
We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same …
We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initializa…
NeuraLUT maps neural networks to lookup tables, reducing latency and improving expressivity.
problem Reducing latency in deep neural networks for FPGA accelerators.
method Mapping entire sub-networks to a single lookup table, introducing skip connections.
result Up to 4.3x lower latency for the same accuracy.
Unified framework sparsifies GNNs for faster inference on large graphs.
problem Space and computational bottlenecks in GNNs due to graph size and connectivity.
method Unified GNN sparsification (UGS) framework that prunes graph adjacency matrix and model weights.
result Graph lottery tickets (GLTs) can be trained in isolation to match full model performance.
Train one network for efficient deployment across many devices.
problem Efficient inference across diverse devices with minimal resource constraints.
method Once-for-All (OFA) network training and progressive shrinking algorithm.
result OFA network achieves state-of-the-art accuracy with significantly reduced training time and resource usage.
Study examines effects of pruning techniques on deep learning models.
problem Understanding the impact of pruning methods on deep learning model structure and dynamics.
method Investigated differences in connectivity and learning dynamics of pruned models using various iterative pruning techniques.
result Emergence of structure in pruned models through magnitude-based unstructured pruning and weight rewinding.
Wasserstein Dropoutcs.LG
Wasserstein Dropout improves uncertainty estimation in neural networks.
problem Estimating neural uncertainties for safe machine learning.
method A purely non-parametric approach using dropout-based sub-network distributions and Wasserstein distance.
result Wasserstein Dropout outperforms state-of-the-art methods in uncertainty estimation.
This paper proposes a novel fault diagnosis approach based on generative adversarial networks (GAN) for imbalanced industrial time series where normal samples are much larger than failure cases. We combine a well-designed feature extractor with GAN to help train the whole network. Aimed at obtaining data distribution a…