activity
20162023
most citedRobust Differentiable SVD

64 citations · 343 across the 44 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2021

An Analysis of Super-Net Heuristics in Weight-Sharing NAS

Kaicheng Yu, René Ranftl, Mathieu Salzmann

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design…

cs.LG20211 cited

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Kaicheng Yu, Rene Ranftl, Mathieu Salzmann

Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically s…

cs.LG2020

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Chen Liu, Mathieu Salzmann, Tao Lin +2

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial…

cs.LG2020

How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS

Kaicheng Yu, Rene Ranftl, Mathieu Salzmann

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design…

cs.LG2019

Contextually Plausible and Diverse 3D Human Motion Prediction

Sadegh Aliakbarian, Fatemeh Sadat Saleh, Lars Petersson +2

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular…

cs.LG2019

Learning Variations in Human Motion via Mix-and-Match Perturbation

Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann +3

Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typi…