15 citations · 49 across the 6 of their papers we have counts for
6 papers · 1 filter
Generalization Comparison of Deep Neural Networks via Output Sensitivity
Mahsa Forouzesh, Farnood Salehi, Patrick Thiran
Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand the…
Learning Hawkes Processes from a Handful of Events
Farnood Salehi, William Trouleau, Matthias Grossglauser +1
Learning the causal-interaction network of multivariate Hawkes processes is a useful task in many applications. Maximum-likelihood estimation is the most common approach to solve t…
An Algorithmic Framework to Control Bias in Bandit-based Personalization
L. Elisa Celis, Sayash Kapoor, Farnood Salehi +1
Personalization is pervasive in the online space as it leads to higher efficiency and revenue by allowing the most relevant content to be served to each user. However, recent studi…
Coordinate Descent with Bandit Sampling
Farnood Salehi, Patrick Thiran, L. Elisa Celis
Coordinate descent methods usually minimize a cost function by updating a random decision variable (corresponding to one coordinate) at a time. Ideally, we would update the decisio…
Stochastic Optimization with Bandit Sampling
Farnood Salehi, L. Elisa Celis, Patrick Thiran
Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the…
Lean From Thy Neighbor: Stochastic & Adversarial Bandits in a Network
L. Elisa Celis, Farnood Salehi
An individual's decisions are often guided by those of his or her peers, i.e., neighbors in a social network. Presumably, being privy to the experiences of others aids in learning…