Jeremiah J. Harmsen
Jeremiah Harmsen joined Google in 2005 where he has founded efforts such as TensorFlow Hub, TensorFlow Serving and the Machine Learning Ninja Rotation. He focuses on creating the ideas, tools and people to help the world use machine learning.
He currently leads the Applied Machine Intelligence group at Google AI Zurich. The team increases the impact of machine learning through consultancy, state-of-the-art infrastructure development, research and education.
Jeremiah received a B.S. degree in electrical engineering and computer engineering (2001), a M.S. degree in electrical engineering (2003), a M.S. degree in mathematics (2005) and a Ph.D. in electrical engineering (2005) from Rensselaer Polytechnic Institute, Troy, NY.
Jeremiah lives by the lake with his wife, son and daughter in Zurich, Switzerland.
Authored Publications
Sort By
Scaling Vision Transformers to 22 Billion Parameters
Josip Djolonga
Basil Mustafa
Piotr Padlewski
Justin Gilmer
Mathilde Caron
Rodolphe Jenatton
Michael Tschannen
Anurag Arnab
Carlos Riquelme
Gamaleldin Elsayed
Fisher Yu
Avital Oliver
Fantine Huot
Mark Collier
Vighnesh Birodkar
Yi Tay
Filip Pavetić
Thomas Kipf
Neil Houlsby
Arxiv (2023)
Preview abstract
The scaling of Transformers has driven breakthrough capabilities for language models.
At present, the largest large language models (LLMs) contain upwards of 100B parameters.
Vision Transformers (ViT) have introduced the same architecture to image and video modeling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters. We present a recipe for highly efficient training of a 22B-parameter ViT and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features) ViT22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between bias and performance, an improved alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT22B demonstrates the potential for "LLM-like'' scaling in vision, and provides key steps towards getting there.
View details
TensorFlow-Serving: Flexible, High-Performance ML Serving
Christopher Olston
Fangwei Li
Jordan Soyke
Kiril Gorovoy
Li Lao
Sukriti Ramesh
Vinu Rajashekhar
Workshop on ML Systems at NIPS 2017
Preview abstract
We describe TensorFlow-Serving, a system to serve machine learning models inside
Google which is also available in the cloud and via open-source. It is extremely
flexible in terms of the types of ML platforms it supports, and ways to
integrate with systems that convey new models and updated versions from training
to serving. At the same time, the core code paths around model lookup and
inference have been carefully optimized to avoid performance pitfalls observed
in naive implementations.
The paper covers the architecture of the extensible serving library, as well as
the distributed system for multi-tenant model hosting. Along the way it points
out which extensibility points and performance optimizations turned out to be
especially important based on production experience.
View details
Wide & Deep Learning for Recommender Systems
Levent Koc
Tal Shaked
Glen Anderson
Wei Chai
Mustafa Ispir
Rohan Anil
Lichan Hong
Vihan Jain
Xiaobing Liu
Hemal Shah
arXiv:1606.07792 (2016)
Preview abstract
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort. With less feature engineering, deep neural networks can generalize better to unseen feature combinations through low-dimensional dense embeddings learned for the sparse features. However, deep neural networks with embeddings can over-generalize and recommend less relevant items when the user-item interactions are sparse and high-rank. In this paper, we present Wide & Deep learning---jointly trained wide linear models and deep neural networks---to combine the benefits of memorization and generalization for recommender systems. We productionized and evaluated the system on a commercial mobile app store with over one billion active users and over one million apps. Online experiment results show that Wide & Deep significantly increased app acquisitions compared with wide-only and deep-only models.
View details
Up Next: Retrieval Methods for Large Scale Related Video Suggestion
Lluis Garcia Pueyo
Vanja Josifovski
Dima Lepikhin
Proceedings of KDD 2014, New York, NY, USA, pp. 1769-1778
Preview abstract
The explosive growth in sharing and consumption of the video content on the web creates a unique opportunity for scientific advances in video retrieval, recommendation and discovery. In this paper, we focus on the task of video suggestion, commonly found in many online applications. The current state-of-the-art video suggestion techniques are based on the collaborative filtering analysis, and suggest videos that are likely to be co-viewed with the watched video. In this paper, we propose augmenting the collaborative filtering analysis with the topical representation of the video content to suggest related videos. We propose two novel methods for topical video representation. The fi rst
method uses information retrieval heuristics such as tf-idf, while the second method learns the optimal topical representations based on the implicit user feedback available in the
online scenario. We conduct a large scale live experiment on YouTube traffic, and demonstrate that augmenting collaborative filtering with topical representations significantly improves the quality of the related video suggestions in a live setting, especially for categories with fresh and topically-rich
video content such as news videos. In addition, we show that employing user feedback for learning the optimal topical video representations can increase the user engagement by more than 80% over the standard information retrieval representation, when compared to the collaborative filtering baseline.
View details
Preview abstract
This work investigates a central problem in steganography, that is: How much data can safely be hidden without being detected? To answer this question, a formal definition of steganographic capacity is presented. Once this has been defined, a general formula for the capacity is developed. The formula is applicable to a very broad spectrum of channels due to the use of an information-spectrum approach. This approach allows for the analysis of arbitrary steganalyzers as well as nonstationary, nonergodic encoder and attack channels. After the general formula is presented, various simplifications are applied to gain insight into example hiding and detection methodologies. Finally, the context and applications of the work are summarized in a general discussion.
View details
