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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “NAS-Bench-201”

BRP-NAS: Prediction-based NAS using GCNscs.LG

BRP-NAS uses GCNs to predict neural network performance for more efficient NAS.

problem Inaccurate performance metrics in NAS lead to suboptimal model designs.

method Proposes BRP-NAS, a hardware-aware NAS using GCNs for accurate performance prediction.

result BRP-NAS outperforms previous methods on NAS-Bench-101 and 201, improving model sample efficiency.

Neural Architecture Search Graph Convolutional Networks Performance Prediction Efficient Deployment NAS-Bench-101

2020-07-16abs ↗pdf ↗

Guided Evolution for Neural Architecture Searchcs.LG

Guided Evolution improves NAS efficiency and accuracy.

problem NAS methods converge to local minima and are complex.

method G-EA: guided evolutionary approach with initialization evaluation and continuous knowledge extraction.

result G-EA achieves state-of-the-art results in CIFAR-10, CIFAR-100, and ImageNet16-120.

Neural Architecture Search Evolutionary Algorithms NAS-Bench-201 CIFAR-10 CIFAR-100

2021-10-28abs ↗pdf ↗

Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importancecs.LG

This study analyzes NAS benchmarks and finds that only a subset of operations is crucial for generating high-performing architectures.

problem NAS benchmarks lack generability and provide skewed performance distributions, leading to unreliable comparisons.

method Empirical analysis of widely used NAS benchmarks (101, 201, TransNAS-Bench-101) focusing on operation importance and generability.

result Only a subset of operations is necessary to generate architectures close to the upper-bound performance range, and convolution layers have the highest impact.

Neural Architecture Search NAS Benchmarks Operation Importance Generability Performance Distribution

2023-03-29abs ↗pdf ↗

One-Shot Neural Architecture Search via Compressive Sensingcs.LG

Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…

2019-06-07abs ↗pdf ↗

Robust NAS under adversarial training: benchmark, theory, and beyondcs.LG

This work benchmarks and theorizes robust NAS under adversarial training.

problem Lack of benchmark evaluations and theoretical guarantees for robust NAS architectures under adversarial training.

method Released a comprehensive data set and established a generalization theory using the neural tangent kernel.

result Established a generalization theory for robust NAS architectures under adversarial training.

NAS robustness adversarial training benchmark theory

2024-03-19abs ↗pdf ↗

DrNAS: Dirichlet Neural Architecture Searchcs.LG

DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.

problem Efficiently search for neural architectures with improved generalization and exploration.

method Formulates architecture search as a distribution learning problem using Dirichlet distribution and gradient-based optimization. Introduces a progressive learning scheme to handle large-scale tasks.

result Achieves state-of-the-art results on CIFAR-10 and ImageNet, demonstrating improved generalization and exploration.

Neural Architecture Search Dirichlet Distribution Gradient-Based Optimization Progressive Learning Generalization

2020-06-18abs ↗pdf ↗

Smooth Variational Graph Embeddings for Efficient Neural Architecture Searchcs.LG

Smooth embedding space improves NAS performance.

problem Efficiently predicting good neural architectures.

method Two-sided variational graph autoencoder.

result Smooth embedding space facilitates extrapolation to unseen architectures.

Neural Architecture Search Variational Autoencoder Graph Embedding Efficient NAS Smooth Reconstruction

2020-10-09abs ↗pdf ↗

Neural Architecture Search without Trainingcs.LG

Automates neural network design without training, speeding up search by seconds.

problem Time and effort in hand-designing deep neural networks.

method Predict trained accuracy from untrained network state using activation overlap.

result Search for powerful networks in seconds, verified on various benchmarks.

Neural Architecture Search NAS Deep Learning Automated Design Activation Overlap

2020-06-08abs ↗pdf ↗

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easycs.LG

NAS-Bench-Suite simplifies NAS evaluation across diverse tasks.

problem Limited and inconsistent NAS benchmarks hinder research reproducibility.

method Developed a comprehensive, extensible NAS benchmark suite.

result Many NAS conclusions do not generalize across different benchmarks.

NAS benchmarks reproducibility generalization neural architecture search

2022-01-31abs ↗pdf ↗

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networkscs.LG

LC-PFN predicts learning curve performance more accurately and faster than MCMC.

problem Bayesian extrapolation of learning curves is computationally expensive and overly restrictive.

method Prior-Data Fitted Neural Networks (PFNs) for approximate Bayesian inference.

result LC-PFN outperforms MCMC in accuracy and is significantly faster.

learning curve extrapolation Bayesian inference PFNs neural networks model selection

2023-10-31abs ↗pdf ↗

Stronger NAS with Weaker Predictorscs.LG

WeakNAS uses a set of weaker predictors to find top architectures with fewer samples.

problem Finding the best neural architecture with heavy computation costs.

method Proposes a paradigm shift from fitting the whole architecture space to progressively fitting a search path through a set of weaker predictors.

result WeakNAS produces coarse-to-fine iteration to gradually refine the ranking of sampling space, requiring fewer samples to find top-performance architectures.

Neural Architecture Search Predictor-based NAS WeakNAS Coarse-to-fine Fewer Samples

2021-02-21abs ↗pdf ↗