From the 1 of 1.7k papers with an AI index.
24.4k citations
- University of California, BerkeleyUS97 papers
- Stanford UniversityUS81 papers
- Massachusetts Institute of TechnologyUS75 papers
- Google DeepMind (United Kingdom)GB60 papers
- Carnegie Mellon UniversityUS54 papers
- University of TorontoCA54 papers
- Princeton UniversityUS51 papers
- Cornell UniversityUS49 papers
- University of Illinois Urbana-ChampaignUS41 papers
- Columbia UniversityUS35 papers
- University of WashingtonUS35 papers
- University of California, Santa BarbaraUS34 papers
29 papers · 2 filters
Measuring the Reliability of Reinforcement Learning Algorithms
Stephanie C. Y. Chan, Samuel Fishman, John Canny +2
Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have g…
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Dan Hendrycks, Norman Mu, Ekin D. Cubuk +3
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated i…
Spatio-Temporal Alignments: Optimal transport through space and time
Hicham Janati, Marco Cuturi, Alexandre Gramfort
Comparing data defined over space and time is notoriously hard, because it involves quantifying both spatial and temporal variability, while at the same time taking into account th…
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
Tor Lattimore, Csaba Szepesvari, Gellert Weisz
The construction by Du et al. (2019) implies that even if a learner is given linear features in that approximate the rewards in a bandit with a uniform error of ,…
Gradient-based Adaptive Markov Chain Monte Carlo
Michalis K. Titsias, Petros Dellaportas
We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets. We define a maximum entropy regu…
Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks
Ben Adlam, Charles Weill, Amol Kapoor
We investigate under and overfitting in Generative Adversarial Networks (GANs), using discriminators unseen by the generator to measure generalization. We find that the model capac…