Why you should not use randomSplit in PySpark to split data into train and test.In case you work with large scale data and want to prepare dataset for your Tensorflow/PyTorch model, don’t use randomSplit function to…Aug 3, 20222Aug 3, 20222
Published inCantor’s ParadiseThe Easiest Unsolved Problem in Graph TheoryGraph theory has a long history of problems being solved by amateur mathematicians. Do you want to try yourself to become one of them?Feb 25, 20216Feb 25, 20216
Published inCriteo Tech BlogTop Applications of Graph Neural Networks 2021GNNs have come a long way in academia. But do we have good applications of them in industry?Jan 14, 2021Jan 14, 2021
Published inCriteo Tech BlogNeurIPS 2020. Comprehensive analysis of authors, organizations, and countries.What will happen at NeurIPS2020 this December? Top authors, affiliations, and countries at the biggest AI Conference of this year analyzed.Oct 15, 20201Oct 15, 20201
Published inCriteo Tech BlogKDD-2020 HighlightsLet’s take a look at some of the highlights of this year’s KDD — one of the biggest applied research conferences in Computer Science.Aug 23, 2020Aug 23, 2020
Published inCriteo Tech BlogCriteo papers at ICML 2020. Online learning, Optimization, and Generative models.High-level discussion of Criteo papers at ICML: Criteo AI Lab has 9 accepted papers at ICML 2020. This is a new record for us!Jun 23, 2020Jun 23, 2020
Published inCriteo Tech BlogICML 2020. Comprehensive analysis of authors, organizations, and countries.Who published the most?Jun 16, 20201Jun 16, 20201
Published inTowards Data ScienceWhy `True is False is False` -> False?Here is a little interview question to you, experienced Python programmer.May 31, 20201May 31, 20201
Published inTowards Data ScienceA forgotten story of Soviet AIWhat it was like to be a programmer 70 years ago?Apr 21, 2020Apr 21, 2020