51 citations · 214 across the 16 of their papers we have counts for
18 papers
Co-design Hardware and Algorithm for Vector Search
Wenqi Jiang, Shigang Li, Yu Zhu +8
Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousand…
Stochastic Gradient Descent without Full Data Shuffle
Lijie Xu, Shuang Qiu, Binhang Yuan +9
Stochastic gradient descent (SGD) is the cornerstone of modern machine learning (ML) systems. Despite its computational efficiency, SGD requires random data access that is inherent…
SHiFT: An Efficient, Flexible Search Engine for Transfer Learning
Cedric Renggli, Xiaozhe Yao, Luka Kolar +3
Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch. The emergence of rich model repositories, such as TensorFlow Hub, enable…
DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses
Alexander Veicht, Cedric Renggli, Diogo Barradas
Website fingerprinting (WF) attacks, usually conducted with the help of a machine learning-based classifier, enable a network eavesdropper to pinpoint which web page a user is acce…
Learning to Merge Tokens in Vision Transformers
Cedric Renggli, André Susano Pinto, Neil Houlsby +3
Transformers are widely applied to solve natural language understanding and computer vision tasks. While scaling up these architectures leads to improved performance, it often come…
Dynamic Human Evaluation for Relative Model Comparisons
Thórhildur Thorleiksdóttir, Cedric Renggli, Nora Hollenstein +1
Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure…
Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee
Cedric Renggli, Luka Rimanic, Nora Hollenstein +1
The Bayes error rate (BER) is a fundamental concept in machine learning that quantifies the best possible accuracy any classifier can achieve on a fixed probability distribution. D…
A Data Quality-Driven View of MLOps
Cedric Renggli, Luka Rimanic, Nezihe Merve Gürel +3
Developing machine learning models can be seen as a process similar to the one established for traditional software development. A key difference between the two lies in the strong…
Decoding EEG Brain Activity for Multi-Modal Natural Language Processing
Nora Hollenstein, Cedric Renggli, Benjamin Glaus +4
Until recently, human behavioral data from reading has mainly been of interest to researchers to understand human cognition. However, these human language processing signals can al…
On Convergence of Nearest Neighbor Classifiers over Feature Transformations
Luka Rimanic, Cedric Renggli, Bo Li +1
The k-Nearest Neighbors (kNN) classifier is a fundamental non-parametric machine learning algorithm. However, it is well known that it suffers from the curse of dimensionality, whi…
Automatic Feasibility Study via Data Quality Analysis for ML: A Case-Study on Label Noise
Cedric Renggli, Luka Rimanic, Luka Kolar +2
In our experience of working with domain experts who are using today's AutoML systems, a common problem we encountered is what we call "unrealistic expectations" -- when users are…
Which Model to Transfer? Finding the Needle in the Growing Haystack
Cedric Renggli, André Susano Pinto, Luka Rimanic +4
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarka…
Scalable Transfer Learning with Expert Models
Joan Puigcerver, Carlos Riquelme, Basil Mustafa +5
Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually ge…
Observer Dependent Lossy Image Compression
Maurice Weber, Cedric Renggli, Helmut Grabner +1
Deep neural networks have recently advanced the state-of-the-art in image compression and surpassed many traditional compression algorithms. The training of such networks involves…
Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment
Cedric Renggli, Bojan Karlaš, Bolin Ding +4
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development. Developing a machine learni…
Distributed Learning over Unreliable Networks
Chen Yu, Hanlin Tang, Cedric Renggli +5
Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e.g., gradients or models), the network should guar…
The Convergence of Sparsified Gradient Methods
Dan Alistarh, Torsten Hoefler, Mikael Johansson +3
Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of comm…
SparCML: High-Performance Sparse Communication for Machine Learning
Cedric Renggli, Saleh Ashkboos, Mehdi Aghagolzadeh +2
Applying machine learning techniques to the quickly growing data in science and industry requires highly-scalable algorithms. Large datasets are most commonly processed "data paral…