SAEP prunes sub-architectures to reduce search cost while maintaining performance.
problem Redundancy in ensemble sub-architectures leads to high computational cost.
method SAEP leverages diversity to prune sub-architectures, reducing ensemble size.
result SAEP reduces the number of sub-architectures without degrading performance.
Bayesian optimization reduces RNN architecture search time.
problem Optimizing RNN architectures for time series prediction.
method Bayesian Optimization with a training-free performance metric.
result BO designs well-performing RNN architectures with reduced optimization time.
Study reduces NAS search cost by generating multiple complex architectures in one shot.
problem Finding multiple neural architectures with varying complexities efficiently.
method Uses importance sampling to generate and update multiple distributions of architectures.
result Reduces search cost by finding multiple architectures with different complexities in a single search.
A method to reduce memory usage in NAS by pruning the search space.
problem High GPU memory consumption in One-Shot NAS techniques.
method Utilising Zero-Shot NAS to prune the search space before applying One-Shot NAS.
result Reduces memory consumption by 81% while maintaining accuracy.
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly applied to large scale problems because of their prohibitive computational complex…
Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network. However, the efficacy of structured pruning has largely evaded scrutiny. In this paper, we examine ResNe…
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…
Hill-climbing is a powerful baseline for NAS, even with reduced noise.
problem Noise in evaluating neural architectures.
method Hill-climbing algorithm, denoising training pipeline.
result Hill-climbing outperforms state-of-the-art NAS algorithms with reduced noise.
A real-time federated neural architecture search approach reduces costs and improves performance.
problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.
SemiNAS reduces NAS cost by predicting accuracy of unlabeled architectures.
problem Costly evaluation of architectures limits NAS efficiency.
method SemiNAS uses unlabeled architectures to train an accuracy predictor.
result SemiNAS achieves comparable accuracy with less data.
A new neural network architecture reduces parameters by 94% while maintaining performance.
problem Reduction of trainable parameters in neural networks.
method Spatially-coupled sparse construction to allocate trainable parameters efficiently.
result Performance comparable to traditional neural networks with 94% fewer parameters.
XferNAS reduces neural architecture search time by 33x.
problem Expensive neural architecture search for new tasks.
method Transfer knowledge from previous tasks to reduce search time.
result Reduction of search time from 200 to 6 GPU days.
This paper improves neural architecture search by focusing on novelty-driven sampling.
problem Lack of positive correlation between validation accuracy and test accuracy in One-Shot NAS.
method Single-path supernet with optimized weights and novelty search for architecture sampling.
result Novelty search method achieves state-of-the-art test error rate on CIFAR-10.
LeanResNet reduces CNN complexity without sacrificing accuracy.
problem High computational cost in CNNs, especially in ResNets.
method Introduces lean convolution operators that reduce parameters and complexity.
result LeanResNet achieves comparable results to other reduced architectures with fewer parameters.
EENA efficiently searches neural architectures with minimal resources.
problem Lack of direction and high computational cost in neural architecture search.
method EENA uses guided evolution with mutation and crossover operations.
result EENA designs highly effective neural architectures with minimal resources.
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. 104 GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…
To solve the big topic modeling problem, we need to reduce both time and space complexities of batch latent Dirichlet allocation (LDA) algorithms. Although parallel LDA algorithms on the multi-processor architecture have low time and space complexities, their communication costs among processors often scale linearly wi…
DSNAS optimizes neural architecture and parameters in one step.
problem Poor correlation between architecture performance in two stages of NAS methods.
method Task-specific end-to-end approach with DSNAS framework.
result DSNAS discovers comparable accuracy networks in less time.
While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by hardware and speed constraints. Conventional model compression methods attempt to address this problem by modifying the architecture manually …
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 distance metric for neural architecture search reduces search space complexity.
problem Reducing the complexity of neural architecture search.
method Fisher task distance for measuring task similarity and online neural architecture search.
result Reduced search space complexity for task-specific architectures.
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.
In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a GNU radio-based data set that mimics the imperfections in a real wireless channe…
We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost. To address this we propose Transfer Neural A…
Reduced numerical precision is a common technique to reduce computational cost in many Deep Neural Networks (DNNs). While it has been observed that DNNs are resilient to small errors and noise, no general result exists that is capable of predicting a given DNN system architecture's sensitivity to reduced precision. In …
This paper compares two GAN architectures to reduce mode collapse.
problem Reducing mode collapse in Generative Adversarial Networks (GANs).
method Explains and compares PacGAN and VEEGAN models.
result PacGAN performs slightly better than vanilla GAN in terms of mode collapse.
Neural networks have proven to be extremely powerful tools for modern artificial intelligence applications, but computational and storage complexity remain limiting factors. This paper presents two compatible contributions towards reducing the time, energy, computational, and storage complexities associated with multil…
GOBO compresses 99.9% of BERT model parameters to 3 bits, improving inference efficiency.
problem Efficient execution of attention-based NLP models, especially in terms of latency and energy consumption.
method GOBO quantizes 32-bit floating-point parameters to 3 bits without fine-tuning, using hardware compression and co-designed architectures.
result GOBO maintains model accuracy while significantly reducing inference latency and energy consumption.
New method reduces NAS search time and complexity.
problem High computational cost and complexity in NAS.
method Differentiable search space with annealing and pruning.
result Achieves 1.68% error on CIFAR-10 with 0.2 GPU days.
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.
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.
We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our approach combines a novel hierarchical genetic representation scheme that imitates the modularized design pattern commonly adopted by human ex…
FedNAS automates federated learning by searching for better architectures.
problem Non-I.I.D. data makes predefined model architectures suboptimal.
method Federated Neural Architecture Search (FedNAS) for collaborative architecture optimization.
result FedNAS searches for better architectures that outperform predefined models.
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 1/mL−1, leading to significant error rate decreases. Motivated by applications in architecture and design, we present a novel method for increasing the developability of a B-spline surface. We use the property that the Gauss image of a developable surface is 1-dimensional and can be locally well approximated by circles. This is cast into an algorithm for thinning the Gau…
SmoothDARTS stabilizes DARTS-based architecture search by smoothing loss landscapes.
problem DARTS-based NAS methods suffer from instability, leading to deteriorating architectures.
method SmoothDARTS (SDARTS) uses perturbation-based regularization to smooth the loss landscape.
result SmoothDARTS improves the generalizability and performance of DARTS-based methods.
Reduces transferability of adversarial examples between models.
problem Transferability of adversarial examples between different models trained on different datasets.
method Investigates the angle between input-output Jacobians of different models to demonstrate relevance and explains asymmetry in terms of gradient norms.
result Simple modification reduces adversarial example transferability between models.
BayesNAS uses Bayesian learning to improve neural architecture search efficiency.
problem Improper treatment of zero operations and architecture parameter pruning issues in one-shot NAS methods.
method Employing hierarchical automatic relevance determination (HARD) priors for Bayesian learning to model architecture parameters.
result Found architecture on CIFAR-10 in just 0.2 GPU days using a single GPU.
FiGS searches over a larger space of architectures for efficient mobile models.
problem Designing small, efficient deep networks for mobile devices.
method Differentiable search method using sparse regularization and Logistic-Sigmoid distribution.
result FiGS produces state-of-the-art parameter-efficient models on ImageNet and improves object detection performance.
This study examines how neural network architecture parameters affect loss surface modality.
problem Understanding the relationship between neural architecture parameters and loss surface modality.
method Fitness landscape analysis of neural network loss surfaces under various architecture settings.
result An increase in problem dimensionality, hidden layer width, and architecture depth affects the modality of loss surfaces.
Optimizes neural architecture search to generate novel lightweight models.
problem Over-reliance on expert knowledge limits NAS to local optima, preventing architectural breakthroughs.
method Casts NAS as an optimization problem, introduces a hierarchical graph-based search space, and uses Bayesian optimization.
result Generates extremely lightweight yet competitive models on six benchmark datasets.
Improved neural architecture search through balanced training.
problem Inconsistent ranking of architectures under one-shot training.
method Balanced NAO: balanced training of supernet during search.
result Significant improvements in architecture discovery and performance.
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely based on their results on the downstream task. While intuitive, …
This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep…
New method reduces neural image compression run-time by 50%.
problem Computational efficiency of neural image compression models.
method Automatic network optimization to reduce decoder complexity.
result Decreased decoder run-time by over 50%.
Enhances crypto-asset AMM with deep learning for better liquidity and efficiency.
problem Reduced slippage and improved liquidity in decentralized finance.
method Deep reinforcement learning for predicting market equilibrium and optimizing liquidity.
result Improved capital efficiency and reduced slippage for crypto-asset traders.
NASIB adapts NAS to varying computation resources efficiently.
problem Constrained computation resources in enterprise environments.
method Adapts exploration vs. exploitation trade-off and uses Superkernels.
result Searches over a larger space with similar accuracy in less time.
HotNAS reduces AI search time from hundreds of GPU hours to less than 3 GPU hours.
problem High time required for AI solution generation from scratch.
method HotNAS starts from a 'hot' state using pre-trained models and integrates compression during co-search.
result Reduces search time from 200 GPU hours to less than 3 GPU hours.