Bytepawn - Marton Trencseni

Training a Pytorch Wasserstein MNIST GAN on Google Colab

Marton Trencseni - Wed 03 March 2021 • Tagged with python, pytorch, torchvision, mnist, gan

I train a Pytorch Wasserstein MNIST GAN on Google Colab to beautiful MNIST digits.

Wasserstein GAN Generated MNIST digits

Training a Pytorch Lightning MNIST GAN on Google Colab

Marton Trencseni - Sat 20 February 2021 • Tagged with python, pytorch, gan, mnist, google-colab

I explore MNIST digits generated by a Generative Adversarial Network trained on Google Colab using Pytorch Lightning.

Softmax GAN after 5 epoch, 100 samples.

Automatic MLFlow logging for Pytorch

Marton Trencseni - Sun 24 January 2021 • Tagged with mlflow, tracking

I explore the automatic logging capabilities of MLFlow for Pytorch.

MLFlow Pytorch loss example.

Automatic MLFlow logging for Scikit Learn

Marton Trencseni - Fri 15 January 2021 • Tagged with mlflow, tracking

I explore the automatic logging capabilities of MLFlow for Scikit Learn. In the process I found a bug in MLFlow, reported it and wrote a pull request to fix it.

MLFlow scatter plot.

Getting Started with MLFlow

Marton Trencseni - Sun 10 January 2021 • Tagged with mlflow, tracking

For the last few months I’ve been using MFlow in production, specifically its Tracking component. MLFlow is an open source project for lifecycle tracking and serving of ML models, coming out of Databricks. MLFlow is model agnostic, so you can use with SKLearn, XGBoost, Pytorch, Tensorflow, FBProphet, anything.

MLFlow overview

Making statistics lie for the 2020 Presidential election

Marton Trencseni - Thu 17 December 2020 • Tagged with ab-testing, trump, politics

After the 2020 US presidential election, the Trump campaign filed over 50 lawsuits and attacked the integrity of the elections by claiming there was voter fraud. One of the last lawsuits was filed in the Supreme Court of the United States by the state of Texas. Here I look at the statistical claims made in this lawsuit that were supposed to show irregularities in the Georgia vote.

Trump vs Biden

Comparing conversion at control and treatment sites

Marton Trencseni - Thu 03 December 2020 • Tagged with ab-testing

In real-life, non-digital situations, it's often not feasible to run true A/B tests. In such cases, we can compare before and after rollout conversions at a treatment site, while using a similar control site to measure and correct for seasonality. The post discusses how to compute increasingly correct p-values and bayesian probabilities in such scenarios.

Monte Carlo simulated control lifts

Unevenness at the edges

Marton Trencseni - Fri 30 October 2020 • Tagged with stats, data

Sometimes we look at the top performers in a field and see obviously uneven representations of groups (gender, ethnicity, etc). There a multitude of factors that can lead to it, such as unfair bias in access to opportunities. Here I will show one unintuitive mathematical effect that can contribute to such unevenness in the case of normal distributions.

Effective Data Visualization Part 3: Line charts and stacked area charts

Marton Trencseni - Tue 01 September 2020 • Tagged with charts, dashboards, data, visualization

Most charts should be line charts or stacked area chart, because they communicate valuable trend information and are easy to parse for the human eyes and brain.

Effective Data Visualization Part 2: Formatting numbers

Marton Trencseni - Sun 23 August 2020 • Tagged with charts, dashboards, data, visualization

Format numbers for human consumption. What is more readable, 1.539e+5 or 153,859? Showing numbers effectively on spreadsheets, charts, dashboards, reports is a basic ingredient for readability, like formatting code in programming.

Effective Data Visualization Part 1: Categorical data

Marton Trencseni - Sat 22 August 2020 • Tagged with charts, dashboards, data, visualization

Making clear, readable charts is part of the craftmanship minimum for any data related role. In part one, I look at how to present categorical data.

A pie chart

Multi-armed bandits and false positives

Marton Trencseni - Fri 21 August 2020 • Tagged with ab-testing

I use Monte Carlo simulations to explore the false positive rate of Multi-armed bandits.

Epsilon-greedy

A/B testing and Multi-armed bandits

Marton Trencseni - Fri 07 August 2020 • Tagged with ab-testing

Multi-armed bandits minimize regret when performing A/B tests, trading off between exploration and exploitation. Monte Carlo simulations shows that less exploration yields less statistical significance.

Epsilon-greedy

Understanding Facebook’s Planout A/B testing framework

Marton Trencseni - Fri 22 May 2020 • Tagged with ab-testing

PlanOut is a framework for online field experiments. It was created by Facebook in 2014 to make it easy to run and iterate on sophisticated experiments in a statistically sound manner.

Planout

Validation checks for A/B tests

Marton Trencseni - Thu 16 April 2020 • Tagged with ab-testing

A/B tests go wrong all the time, even in sophisticated product teams. As this article shows, for a range of problems we can run automated validation checks to catch problems early, before they have too bad of an effect on customers or the business. These validation checks compare various statistical properties of the funnels A and B to catch likely problems. Large technology companies are running such validation checks automatically and continuously for their online experiments.

Kolmogorov-Smirnov test

Running multiple A/B tests in parallel

Marton Trencseni - Mon 06 April 2020 • Tagged with ab-testing

I show using Monte Carlo simulations that randomizing user assignments into A/B test experiments makes it possible to run multiple A/B tests at once and measure accurate lifts on the same metric, assuming the experiments are independent.

Watts-Strogatz

Bayesian A/B conversion tests

Marton Trencseni - Tue 31 March 2020 • Tagged with bayesian, ab-testing

I compare probabilities from Bayesian A/B testing with Beta distributions to frequentist A/B tests using Monte Carlo simulations. Under a lot of circumstances, the bayesian probability of the action hypothesis being true and the frequentist p value are complementary.

Bayes vs z-test