2226 results for "earn" across all locations
UberMENTOR: Meet with Chicago’s Best and Brightest
Entrepreneurs, young professionals, and aspiring executives — your opportunity to learn from Chicago’s best and brightest is just a tap away.
On January 21st, request UberMENTOR for a chance to ride with one of Chicago’s top leaders from 1871, Techweek, ContextMedia, Leo Burnett, Future Founders and more—brought to you by the Startup Institute. Find out how to request and learn more about each of the mentors below.
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
Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
S. Gu, T. Lillicrap, Z. Ghahramani, R. Turner, S. Levine
Model-free deep reinforcement learning (RL) methods have been successful in a wide variety of simulated domains. However, a major obstacle facing deep RL in the real world is their high sample complexity. […] [PDF]
International Conference on Learning Representations (ICLR), 2016
Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
J. Zhang, Y. Wang, P. Molino, L. Li, D. Ebert
Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation, debugging, and comparison of machine learning models in a more transparent and interactive manner. […] [PDF]
IEEE Visualization (IEEE VIS), 2018
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
M. T. Law, J. Snell, A.-M. Farahmand, R. Urtasun, R. S. Zemel
Most deep learning models rely on expressive high-dimensional representations to achieve good performance on tasks such as classification. However, the high dimensionality of these representations makes them difficult to interpret and prone to over-fitting. We propose a simple, intuitive and scalable dimension reduction framework that takes into account the soft probabilistic interpretation of standard deep models for classification. […] [PDF]
International Conference on Learning Representations (ICLR), 2019
Navy Region Southwest
Navy Region Southwest (NRSW) allows eligible drivers to make pickups and dropoffs at their naval bases in San Diego. Learn how you can start accessing the bases to cash in on the action.
Uber Goes to NeurIPS 2019
Uber is presenting 11 papers at the NeurIPS 2019 conference in Vancouver, Canada, as well as sponsoring workshops including Women in Machine Learning (WiML) and Black in AI.
Uber Visualization Highlights: Displaying City Street Speed Clusters with SpeedsUp
As part of Uber Visualization’s all-team hackathon, we built SpeedsUp, a project using machine learning to process average speeds across a city, cluster the results, and overlay them on a street map.
How Kolkata Chai Co. used Vouchers to thank its community
For Kolkata Chai Co., the pandemic added an extra layer of challenge. Learn how offerings like a DIY chai kit and Vouchers to use on Uber helped them weather the storm.
Network IDS Ruleset Management with Aristotle v2
Overwhelmed with network security events? Learn how Uber’s Cyber Defense team programmatically manages network IDS rulesets, augments alerts for correlation, and open-sourced the code they use to do it.