A. Durand

Publications33
h-index11
Citations334
Highly Influential Citations21
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • S. Ahmed
  • 124 Publications, 6,259 Citations
  • P. Abbeel
  • 452 Publications, 46,199 Citations
  • Branislav Kveton
  • 109 Publications, 1,950 Citations
  • S. Levine
  • 310 Publications, 32,115 Citations
  • Publications
  • Influence
Ventral Tegmental Area Cannabinoid Type-1 Receptors Control Voluntary Exercise Performance
BACKGROUND We have shown that the endogenous stimulation of cannabinoid type-1 (CB₁) receptors is a prerequisite for voluntary running in mice, but the precise mechanisms through which the… Expand
  • 85
  • 5
Neuronal representation of individual heroin choices in the orbitofrontal cortex
Drug addiction is a harmful preference for drug use over and at the expense of other non‐drug‐related activities. We previously identified in the rat orbitofrontal cortex (OFC) a mechanism that… Expand
  • 15
  • 3
Streaming kernel regression with provably adaptive mean, variance, and regularization
TLDR
We tackle the problem of tuning the regularization parameter adaptively at each time step, while maintaining tight confidence bounds estimates on the value of the mean function at each point. Expand
  • 17
  • 3
  • PDF
Bayesian optimization for conditional hyperparameter spaces
TLDR
We propose and examine the behavior of two kernels, a conditional kernel which forces the similarity of two samples from different condition branches to be zero, based on similarities with Mondrian processes and random forests. Expand
  • 19
  • 2
  • PDF
Online Adaptative Curriculum Learning for GANs
TLDR
We propose a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. Expand
  • 19
  • 2
  • PDF
Thompson Sampling for Combinatorial Bandits and its Application to Online Feature Selection
In this work, we address the combinatorial optimization problem in the stochastic bandit setting with bandit feedback. We propose to use the seminal Thompson Sampling algorithm under an assumption on… Expand
  • 14
  • 2
  • PDF
Leveraging exploration in off-policy algorithms via normalizing flows
TLDR
We extend SAC to a richer class of probability distributions through normalizing flows, which we show improves performance in exploration, sample complexity, and convergence. Expand
  • 14
  • 2
  • PDF
Machine Learning to Predict Osteoporotic Fracture Risk from Genotypes
Background Genomics-based prediction could be useful since genome-wide genotyping costs less than many clinical tests. We tested whether machine learning methods could provide a clinically-relevant… Expand
  • 6
  • 1
  • PDF
Leveraging Observations in Bandits: Between Risks and Benefits
TLDR
We introduce a new bandit optimism modifier that uses conditional optimism contingent on the actions of the target in order to guide the agent's exploration in the multi-armed bandits setting. Expand
  • 3
  • 1
Bayesian classification and unsupervised learning for isolating weeds in row crops
TLDR
This paper presents a weed/crop classification method using computer vision and morphological analysis to identify weeds present in corn and soybean fields. Expand
  • 35
  • PDF