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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “ProxylessNAS”

Neural Predictor for Neural Architecture Searchcs.LG

Simpler neural architecture search method using random architectures and regression.

problem Complex algorithms in neural architecture search.

method Train N random architectures, use them to train a regression model, predict validation accuracies, and select top-K architectures.

result More sample efficient and competitive with complex approaches.

Neural Architecture Search Regression Model Random Architectures Sample Efficiency ProxylessNAS

2019-12-02abs ↗pdf ↗

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecs.LG

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. $10^4$ GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…

2018-12-02abs ↗pdf ↗

UNAS: Differentiable Architecture Search Meets Reinforcement Learningcs.LG

UNAS combines DNAS and RL for efficient architecture search.

problem Discovering high accuracy or low latency neural architectures.

method Unified framework combining differentiable and reinforcement learning approaches.

result UNAS achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets.

Neural Architecture Search Differentiable NAS Reinforcement Learning Generalization Gap MobileNetV2

2019-12-16abs ↗pdf ↗

APQ: Joint Search for Network Architecture, Pruning and Quantization Policycs.LG

APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.

problem Efficient deep learning inference on resource-constrained hardware.

method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.

result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.

deep learning inference optimization resource-constrained hardware joint optimization quantization

2020-06-15abs ↗pdf ↗