Skip to footer
Home Authors Posts by

Avatar
501 BLOG ARTICLES 186 RESEARCH PAPERS
Co-Founder & CEO of Otto Radio. Passionate about anything tech & cars.

Engineering Blog Articles

Listen to Personalized Podcasts and Audio News Timed to Your Uber Ride

0

By Stanley Yuan

Otto Radio changes the way you listen to talk radio by curating playlists of audio stories personalized to your interests. You can get your own front page of news read to you and discover podcasts you’ll love …

Research Papers

Physically Realizable Adversarial Examples for LiDAR Object Detection

J. Tu, M.Ren, S.Manivasagam, B. Yang, M. Liang, R. Du, F.Cheng, R. Urtasun
Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Despite the fact that this poses a security concern for the self-driving industry, there has been very little exploration in terms of 3D perception, as most adversarial attacks have only been applied to 2D flat images. [...] [PDF]
Computer Vision and Pattern Recognition (CVPR), 2017

First-Order Preconditioning via Hypergradient Descent

T. Moskovitz, R. Wang, J. Lan, S. Kapoor, T. Miconi, J. Yosinski, A. Rawal
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence. Unfortunately, such algorithms typically struggle to scale to high-dimensional problems, in part because the calculation of specific preconditioners such as the inverse Hessian or Fisher information matrix is highly expensive. We introduce first-order preconditioning (FOP), a fast, scalable approach that generalizes previous work on hypergradient descent (Almeida et al., 1998; Maclaurin et al., 2015; Baydin et al.,2017) to learn a preconditioning matrix that only makes use of first-order information. [...] [PDF]
Conference on Neural Information Processing Systems (NeurlPS), 2019

Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

J. Zhi, R. Wang, J. Clune, K. Stanley
Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need for dynamic scaling, and the need for a user interface with low adoption cost and consistency across different backends. In this paper we address these challenges while still retaining development efficiency and flexibility for both research and practical applications by introducing Fiber, a scalable distributed computing framework for RL and population-based methods. [...] [PDF]
arXiv

Estimating Q(s,s’) with Deep Deterministic Dynamics Gradients

A. Edwards, Himanshu Sahni, R. Liu, J. Hung, A. Jain, R. Wang, A. Ecoffet, T. Miconi, C. Isbell, J. Yosinski
In this paper, we introduce a novel form of value function, Q(s,s′), that expresses the utility of transitioning from a state s to a neighboring state s′ and then acting optimally thereafter. In order to derive an optimal policy, we develop a forward dynamics model that learns to make next-state predictions that maximize this value. [...] [PDF]
International Conference on Machine Learning (ICML), 2020

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

R. Wang, J. Lehman, A. Rawal, J. Zhi, Y. Li, J. Clune, K. Stanley
Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. [...] [PDF]
International Conference on Machine Learning (ICML), 2020

Heterogeneous Causal Learning for Effectiveness Optimization in User Marketing

W. Y. Zou, S. Du, J. Lee, J. Pedersen
User marketing is a key focus of consumer-based internet companies. Learning algorithms are effective to optimize marketing campaigns which increase user engagement, and facilitates cross-marketing to related products. By attracting users with rewards, marketing methods are effective to boost user activity in the desired products. Rewards incur significant cost that can be off-set by increase in future revenue. [...] [PDF]
2020

Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects

W. Y. Zou, S. Shyam, M. Mui, M. Wang, J. Pedersen, Z. Ghahramani
Causal inference methods are widely applied in the fields of medicine, policy, and economics. Central to these applications is the estimation of treatment effects to make decisions. Current methods make binary yes-or-no decisions based on the treatment effect of a single outcome dimension. These methods are unable to capture continuous space treatment policies with a measure of intensity. [...] [PDF]
2020

Discovering Essential Multiple Gene Effects through Large Scale Optimization: an Application to Human Cancer Metabolism

T. Durieux, Y. Hamadi, M. Monperrus
Over the last few years, the complexity of web applications has increased to provide more dynamic web applications to users. The drawback of this complexity is the growing number of errors in the front‐end applications. In this paper, we present an approach to provide self‐healing for the web. [...] [PDF]
Software Testing Verification and Reliability 30(2), March 2018

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

S. Dathathri, A. Madotto, J. Lan, J. Hung, E. Frank, P. Molino, J. Yosinski, R. Liu
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying the model architecture or fine-tuning on attribute-specific data and entailing the significant cost of retraining. We propose a simple alternative: the Plug and Play Language Model (PPLM) for controllable language generation, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM. [PDF]
International Conference on Learning Representations (ICLR), 2020

Fully Automated HTML and JavaScript Rewriting for Constructing a Self‐healing Web Proxy

T. Durieux, Y. Hamadi, M. Monperrus
Over the last few years, the complexity of web applications has increased to provide more dynamic web applications to users. The drawback of this complexity is the growing number of errors in the front‐end applications. In this paper, we present an approach to provide self‐healing for the web. [...] [PDF]
Software Testing Verification and Reliability 30(2), March 2018

Joint Interaction and Trajectory Prediction for Autonomous Driving using Graph Neural Networks

D. Lee, Y. Gu, J. Hoang, M. Marchetti-Bowick
Using weakly intent label can potentially predict the interaction and the resulting trajectory better. We use a GNN to model the interaction. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019