1 citations · 1 across the 4 of their papers we have counts for
5 papers
WinoTS: Wavelet-based Self-Distillation for Time Series Models
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised pre-training of time series models is currently dominated by next-token prediction and reconstruction objectives. In continuous-valued domains, these paradigms ofte…
When Does Self-Supervised Learning Transfer to Time-Series Tasks?
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised learning (SSL) assumes that solving pretext tasks on unlabeled data yields representations that transfer effectively across downstream applications via linear probi…
Differentially Private Explanations for Clusters
Amir Gilad, Tova Milo, Kathy Razmadze +1
The dire need to protect sensitive data has led to various flavors of privacy definitions. Among these, Differential privacy (DP) is considered one of the most rigorous and secure…
Learning Approximation Sets for Exploratory Queries
Susan B. Davidson, Tova Milo, Kathy Razmadze +1
In data exploration, executing complex non-aggregate queries over large databases can be time-consuming. Our paper introduces a novel approach to address this challenge, focusing o…
Selecting Sub-tables for Data Exploration
Kathy Razmadze, Yael Amsterdamer, Amit Somech +2
We present a framework for creating small, informative sub-tables of large data tables to facilitate the first step of data science: data exploration. Given a large data table tabl…