Category: FAANG

This paper was accepted at the workshop “Self-Supervised Learning – Theory and Practice” at NeurIPS 2022. Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with respect to the target label distribution. This in turn moves the learned …

Read more “Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer”

A key challenge in many modern data analysis tasks is that user data is heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distribution. This is true, for example in language data, where different speech styles result in data …

Read more “Mean Estimation with User-level Privacy under Data Heterogeneity”

This paper was accepted at the workshop “I Can’t Believe It’s Not Better: Understanding Deep Learning Through Empirical Falsification” Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and generating pseudo-labels (PLs) with …

Read more “Continuous Soft Pseudo-Labeling in ASR”

By: Peter Cioni (Netflix), Alex Schworer (Netflix), Mac Moore (Conductor Tech.), Rachel Kelley (AWS), Ranjit Raju (AWS) Rendering is core to the VFX process VFX studios around the world create amazing imagery for Netflix productions. Nearly every show that is produced today includes digital visual effects, from the creatures in Stranger Things, to recreating historic London in …

Read more “Helping VFX studios pave a path to the cloud”