2019-02-06 Wednesday - Interesting Kaggle Competition, $50K Prize

LANL Earthquake Prediction

Can you predict upcoming laboratory earthquakes?
https://www.kaggle.com/c/LANL-Earthquake-Prediction
$50,000 Prize Money

"Forecasting earthquakes is one of the most important problems in Earth science because of their devastating consequences. Current scientific studies related to earthquake forecasting focus on three key points: when the event will occur, where it will occur, and how large it will be."
"In this competition, you will address when the earthquake will take place. Specifically, you’ll predict the time remaining before laboratory earthquakes occur from real-time seismic data."
"If this challenge is solved and the physics are ultimately shown to scale from the laboratory to the field, researchers will have the potential to improve earthquake hazard assessments that could save lives and billions of dollars in infrastructure."
"This challenge is hosted by Los Alamos National Laboratory which enhances national security by ensuring the safety of the U.S. nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to energy, environment, infrastructure, health, and global security concerns."

2019-02-06 Wednesday - An Interesting ML Paper

Go-Explore: A New Type of Algorithm for Hard-exploration Problems
https://www.youtube.com/watch?v=SWcuTgk2di8

Go-Explore: a New Approach for Hard-Exploration Problems
https://arxiv.org/abs/1901.10995

"A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to improve performance on hard-exploration domains. To address this shortfall, we introduce a new algorithm called Go-Explore. It exploits the following principles: (1) remember previously visited states, (2) first return to a promising state (without exploration), then explore from it, and (3) solve simulated environments through any available means (including by introducing determinism), then robustify via imitation learning. The combined effect of these principles is a dramatic performance improvement on hard-exploration problems. On Montezuma's Revenge, Go-Explore scores a mean of over 43k points, almost 4 times the previous state of the art. Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge. Its max performance of nearly 18 million surpasses the human world record, meeting even the strictest definition of "superhuman" performance. On Pitfall, Go-Explore with domain knowledge is the first algorithm to score above zero. Its mean score of almost 60k points exceeds expert human performance. Because Go-Explore produces high-performing demonstrations automatically and cheaply, it also outperforms imitation learning work where humans provide solution demonstrations. Go-Explore opens up many new research directions into improving it and weaving its insights into current RL algorithms. It may also enable progress on previously unsolvable hard-exploration problems in many domains, especially those that harness a simulator during training (e.g. robotics). "

2018-11-20 Tuesday - Machine Learning Technical Debt and Anti-Patterns

This posting is a placeholder for links to interesting articles/papers that touch on technical debit and anti-patterns in Machine Learning algorithms/models/solutions.

Hidden Technical Debt in Machine Learning Systems
https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf

"Machine learning offers a fantastically powerful toolkit for building useful complex prediction systems quickly. This paper argues it is dangerous to think of these quick wins as coming for free. Using the software engineering framework of technical debt, we find it is common to incur massive ongoing maintenance costs in real-world ML systems. We explore several ML-specific risk factors to account for in system design. These include boundary erosion, entanglement, hidden feedback loops, undeclared consumers, data dependencies, configuration issues, changes in the external world, and a variety of system-level anti-patterns."

A  Convex Framework for Fair Regression

https://arxiv.org/abs/1706.02409

https://arxiv.org/pdf/1706.02409.pdf

"The widespread use of machine learning to make consequential decisions about individual citizens (including in domains such as...criminal sentencing has been accompanied by increased reports of instances in which the algorithms and models employed can be unfair or discriminatory in a variety of ways ...we introduce a rich family of fairness metrics for regression models that take the form of a fairness regularizer and apply them to the standard loss functions for linear and logistic regression." 

"Since these loss functions and our fairness regularizer are convex, the combined objective functions obtained from our framework are also convex, and thus permit efficient optimization. Furthermore, our family of fairness metrics covers the spectrum from the type of group fairness that is common in classification formulations (where e.g. false arrests in one racial group can be “compensated” for by false arrests in another racial group) to much stronger notions of individual fairness (where such cancellations are forbidden, and every injustice is charged to the model). Intermediate fairness notions are also covered. Our framework also permits one to either forbid the use of a "protected” variable (such as race), by demanding that a single model be learned across all groups, or to build different group-dependent models." 

"Most importantly, by varying the weight on the fairness regularizer, our framework permits us to compute the entire “Pareto curve” or efficient frontier of the trade-off between predictive accuracy and fairness.  Such curves are especially important to examine and understand in a domain-specific manner: since demanding fairness of models will always come at a cost of reduced predictive accuracy , it behooves practitioners working with fairness-sensitive data sets to understand just how mild or severe this trade-off is in their particular arena, permitting them to make informed modeling and policy decisions""...in this work we have studied a variety of fairness regularizers for regression problems, and applied them to data sets in which fairness is not subservient to generalization, but is instead a first-order consideration. Our empirical study has demonstrated that the choice of fairness regularizer (group, individual, hybrid, or other) and the particular data set can have qualitative effects on the trade-off between accuracy and fairness...." 

"The Communities and Crime dataset, from the UCI repository is a dataset which includes many features deemed relevant to violent crime rates (such as the percentage of the community’s population in an urban area, the community’s racial makeup, law enforcement involvement and racial makeup of that law enforcement in a community, amount a community’s law enforcement allocated to drug units) for different communities. This data is provided to train regression models based on this data to predict the amount of violent crime (murder, rape, robbery, and assault) in a given community...." 

"The COMPAS dataset The COMPAS dataset contains data from Broward County, Florida originally compiled by ProPublica in which the goal is to predict whether a convicted individual would commit a violent crime in the following two years or not. ..." 

2016-04-20 Wednesday - Exploring Apache SINGA 0.3.0, A General Distributed Deep Learning Platform

Exploring today's Apache SINGA 0.3.0 release, A General Distributed Deep Learning Platform
http://singa.apache.org/docs/overview.html

"SINGA is a general distributed deep learning platform for training big deep learning models over large datasets. It is designed with an intuitive programming model based on the layer abstraction. A variety of popular deep learning models are supported, namely feed-forward models including convolutional neural networks (CNN), energy models like restricted Boltzmann machine (RBM), and recurrent neural networks (RNN). Many built-in layers are provided for users. SINGA architecture is sufficiently flexible to run synchronous, asynchronous and hybrid training frameworks. SINGA also supports different neural net partitioning schemes to parallelize the training of large models, namely partitioning on batch dimension, feature dimension or hybrid partitioning."