Publications by Farnood Salehi

Generalization Comparison of Deep Neural Networks via Output Sensitivity

Patrick Thiran, Farnood Salehi, Mahsa Forouzesh

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 their generalization properties. We shed light on this matter by linking the lo ...

IEEE2021

Augmenting and Tuning Knowledge Graph Embeddings

Farnood Salehi

Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparam ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2020

Multi-armed Bandits in Action

Farnood Salehi

Making decisions is part and parcel of being human. Among a set of actions, we want to choose the one that has the highest reward. But the uncertainty of the outcome prevents us from always making the right decision. Making decisions under uncertainty can ...

EPFL2020

Learning Hawkes Processes from a Handful of Events

Patrick Thiran, Matthias Grossglauser, William Trouleau, Farnood Salehi

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 the problem in the presence of long observation sequences. However, when only ...

2019

A dashboard for controlling polarization in personalization

Nisheeth Vishnoi, Farnood Salehi, Laura Elisa Celis, Vijay Keswani, Sayash Kapoor

Personalization is pervasive in the online space as it leads to higher efficiency for the user and higher revenue for the platform by individualizing the most relevant content for each user. However, recent studies suggest that such personalization can lea ...

IOS PRESS2019

Controlling Polarization in Personalization: An Algorithmic Framework

Nisheeth Vishnoi, Farnood Salehi, Laura Elisa Celis, Sayash Kapoor

Personalization is pervasive in the online space as it leads to higher efficiency for the user and higher revenue for the platform by individualizing the most relevant content for each user. However, recent studies suggest that such personalization can lea ...

ASSOC COMPUTING MACHINERY2019

Coordinate Descent with Bandit Sampling

Patrick Thiran, Farnood Salehi, Laura 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 decision variable that yields the largest decrease in the cost function. However, f ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018