47 citations · 146 across the 12 of their papers we have counts for
13 papers
Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees
Jue Wang, Binhang Yuan, Luka Rimanic +5
Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks. Despite recent intensive…
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…
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…
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic +2
Despite the great successes achieved by deep neural networks (DNNs), recent studies show that they are vulnerable against adversarial examples, which aim to mislead DNNs by adding…
DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Boxin Wang, Fan Wu, Yunhui Long +3
Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training…
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…
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…
TSS: Transformation-Specific Smoothing for Robustness Certification
Linyi Li, Maurice Weber, Xiaojun Xu +5
As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislea…
Lonely runners in function fields
Sam Chow, Luka Rimanic
The lonely runner conjecture, now over fifty years old, concerns the following problem. On a unit length circular track, consider runners starting at the same time and place, e…
Szemerédi's theorem in the primes
Luka Rimanic, Julia Wolf
Green and Tao famously proved in 2005 that any subset of the primes of fixed positive density contains arbitrarily long arithmetic progressions. Green had previously shown that in…
On side lengths of corners in positive density subsets of the Euclidean space
Polona Durcik, Vjekoslav Kovač, Luka Rimanić
We generalize a result by Cook, Magyar, and Pramanik [3] on three-term arithmetic progressions in subsets of to corners in subsets of $\mathbb{R}^d\times\mathbb{R}^d…