pith. machine review for the scientific record. sign in

arxiv: 1611.01578 · v2 · submitted 2016-11-05 · 💻 cs.LG · cs.AI· cs.NE

Recognition: unknown

Neural Architecture Search with Reinforcement Learning

Barret Zoph , Quoc V. Le
Authors on Pith no claims yet
classification 💻 cs.LG cs.AIcs.NE
keywords modelcellneuralstate-of-the-artachievesarchitecturelearningnetworks
0
0 comments X
read the original abstract

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

    cs.CL 2026-05 conditional novelty 8.0

    AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning task...

  2. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

    cs.CL 2026-05 unverdicted novelty 7.0

    AutoTTS discovers superior test-time scaling strategies for LLMs via cheap controller synthesis in a pre-collected trajectory environment, outperforming manual baselines on math benchmarks with low discovery cost.

  3. AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

    cs.CL 2026-04 unverdicted novelty 7.0

    AutoSOTA uses eight specialized agents to replicate and optimize models from recent AI papers, producing 105 new SOTA results in about five hours per paper on average.

  4. RELO: Reinforcement Learning to Localize for Visual Object Tracking

    cs.CV 2026-05 unverdicted novelty 6.0

    RELO replaces handcrafted spatial priors with a reinforcement learning policy for target localization in visual tracking and reports 57.5% AUC on LaSOText without template updates.

  5. OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms

    cs.AI 2026-04 unverdicted novelty 6.0

    OMEGA framework generates novel ML classifiers via meta-prompts and executable code that outperform scikit-learn baselines on 20 benchmark datasets.

  6. TRON: Trainable, architecture-reconfigurable random optical neural networks

    physics.optics 2026-04 unverdicted novelty 6.0

    TRON demonstrates a trainable and reconfigurable optical neural network that combines multi-scattering media with DMD-based matrix multiplication and performs in-situ optimization plus neural architecture search on th...

  7. LLaVA-Video: Video Instruction Tuning With Synthetic Data

    cs.CV 2024-10 unverdicted novelty 6.0

    LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.

  8. Heterogeneous Connectivity in Sparse Networks: Fan-in Profiles, Gradient Hierarchy, and Topological Equilibria

    cs.LG 2026-04 unverdicted novelty 5.0

    Arbitrary heterogeneous fan-in profiles in sparse networks match uniform random accuracy at high sparsity, but initializing RigL dynamic sparse training with equilibrium-matched lognormal profiles improves performance...

  9. From LLM to Silicon: RL-Driven ASIC Architecture Exploration for On-Device AI Inference

    cs.AR 2026-04 unverdicted novelty 5.0

    An RL agent using Soft Actor-Critic with Mixture-of-Experts jointly optimizes ASIC architecture, memory hierarchy, and partitioning for AI inference, achieving 29809 tokens/s for Llama 3.1 at 3nm and under 13mW for Sm...

  10. Efficient Accelerated Graph Edit Distance Computation on GPU

    cs.DC 2026-03 unverdicted novelty 5.0

    FAST-GED delivers orders-of-magnitude speedups over NetworkX for graph edit distance on GPUs while often reaching optimal solutions and outperforming approximate methods.

  11. BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH

    cs.LG 2026-04 unverdicted novelty 4.0

    BayMOTH unifies meta-Bayesian optimization with a usefulness-based fallback to lookahead, demonstrating competitive results on function optimization tasks even under low task relatedness.

  12. Split and Aggregation Learning for Foundation Models Over Mobile Embodied AI Network (MEAN): A Comprehensive Survey

    cs.IT 2026-05 unverdicted novelty 3.0

    The paper surveys split and aggregation learning for foundation models in 6G networks to improve efficiency, resource use, and data privacy in distributed AI.