홈 › Papers

Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar

2019-05-24 · Iddo Drori, Yamuna Krishnamurthy, Raoni Lourenco, Remi Rampin, Kyunghyun Cho, Claudio Silva, Juliana Freire

Automatic machine learning is an important problem in the forefront of machine learning. The strongest AutoML systems are based on neural networks, evolutionary algorithms, and Bayesian optimization. Recently AlphaD3M reached state-of-the-art results with an order of magnitude speedup using reinforcement learning with self-play. In this work we extend AlphaD3M by using a pipeline grammar and a pre-trained model which generalizes from many different datasets and similar tasks. Our results demonstrate improved performance compared with our earlier work and existing methods on AutoML benchmark datasets for classification and regression tasks. In the spirit of reproducible research we make our data, models, and code publicly available.

📄 PDF Abstract BibTeX arXiv:1905.10345

Code (0)

등록된 구현이 없습니다.

Tasks

AutoMLBayesian OptimizationBIG-bench Machine LearningEvolutionary AlgorithmsGeneral ClassificationModel-based Reinforcement Learningregression reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

AlphaD3M: Machine Learning Pipeline Synthesis

2021-11-03 · Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni de Paula Lourenco 외

We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play. AlphaD3M is based on edit operations performed over machine learning pipelin…

AutoML BIG-bench Machine Learning Meta Reinforcement Learning reinforcement-learning+2

Overfitting in Synthesis: Theory and Practice (Extended Version)

2019-05-17 · Saswat Padhi, Todd Millstein, Aditya Nori, Rahul Sharma

In syntax-guided synthesis (SyGuS), a synthesizer's goal is to automatically generate a program belonging to a grammar of possible implementations that meets a logical specification. We investigate a common limitation ac…

Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars

2017-04-01 · Chenfanfu Jiang, Siyuan Qi, Yixin Zhu, Siyuan Huang 외

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the …

Benchmarking Object Scene Understanding Semantic Segmentation

Learning a Meta-Solver for Syntax-Guided Program Synthesis

2019-05-01 · ICLR 2019 5 · Xujie Si, Yuan Yang, Hanjun Dai, Mayur Naik 외

We study a general formulation of program synthesis called syntax-guided synthesis(SyGuS) that concerns synthesizing a program that follows a given grammar and satisfies a given logical specification. Both the logical sp…

Graph Neural Network Meta-Learning Program Synthesis Reinforcement Learning

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

2018-05-11 · ICLR 2018 1 · Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh 외

Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence …

Machine Translation Program Synthesis reinforcement-learning Reinforcement Learning+1