papers

Publications (15)

cs.RO2023

Discovering Adaptable Symbolic Algorithms from Scratch

Stephen Kelly, Daniel S. Park, Xingyou Song +8

Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based…

cs.LG2021

PyGlove: Symbolic Programming for Automated Machine Learning

Daiyi Peng, Xuanyi Dong, Esteban Real +7

Neural networks are sensitive to hyper-parameter and architecture choices. Automated Machine Learning (AutoML) is a promising paradigm for automating these choices. Current ML soft…

cs.NE2026

AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions

Esteban Real, Mirko Rossini, Connal de Souza +7

Transcendental functions, such as the exponential, are central to scientific computing, yet they cannot be natively calculated by digital hardware. Instead, computers must approxim…

cs.LG2023

PyGlove: Efficiently Exchanging ML Ideas as Code

Daiyi Peng, Xuanyi Dong, Esteban Real +2

The increasing complexity and scale of machine learning (ML) has led to the need for more efficient collaboration among multiple teams. For example, when a research team invents a…

cs.CV2015

Attention for Fine-Grained Categorization

Pierre Sermanet, Andrea Frome, Esteban Real

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained…

cs.NE2017

Large-Scale Evolution of Image Classifiers

Esteban Real, Sherry Moore, Andrew Selle +5

Neural networks have proven effective at solving difficult problems but designing their architectures can be challenging, even for image classification problems alone. Our goal is…

cs.CV2017

YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video

Esteban Real, Jonathon Shlens, Stefano Mazzocchi +2

We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximat…

cs.LG2024

Guided Evolution with Binary Discriminators for ML Program Search

John D. Co-Reyes, Yingjie Miao, George Tucker +2

How to automatically design better machine learning programs is an open problem within AutoML. While evolution has been a popular tool to search for better ML programs, using learn…

cs.LG2020

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch

Esteban Real, Chen Liang, David R. So +1

Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has also made si…

cs.NE2019

Regularized Evolution for Image Classifier Architecture Search

Esteban Real, Alok Aggarwal, Yanping Huang +1

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms h…

cs.LG2023

Symbolic Discovery of Optimization Algorithms

Xiangning Chen, Chen Liang, Da Huang +9

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient sea…

cs.LG2019

NAS-Bench-101: Towards Reproducible Neural Architecture Search

Chris Ying, Aaron Klein, Esteban Real +3

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to r…

cs.LG2023

Unified Functional Hashing in Automatic Machine Learning

Ryan Gillard, Stephen Jonany, Yingjie Miao +7

The field of Automatic Machine Learning (AutoML) has recently attained impressive results, including the discovery of state-of-the-art machine learning solutions, such as neural im…

cs.LG2022

Evolving Reinforcement Learning Algorithms

John D. Co-Reyes, Yingjie Miao, Daiyi Peng +5

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-…

cs.LG2023

Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability

Juan Jose Garau-Luis, Yingjie Miao, John D. Co-Reyes +4

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can…