In the past few years, several new matching models have been proposed and studied that take into account complex distributional constraints. Relevant lines of work include (1) school choice with diversity constraints where students have (possibly overlapping) types and (2) hospital-doctor matching where various regional quotas are imposed. In this paper, we present a polynomial-time reduction to transform an instance of (1) to an instance of (2) and we show how the feasibility and stability of corresponding matchings are preserved under the reduction. Our reduction provides a formal connection between two important strands of work on matching with distributional constraints. We then apply the reduction in two ways. Firstly, we show that it is NP-complete to check whether a feasible and stable outcome for (1) exists. Due to our reduction, these NP-completeness results carry over to setting (2). In view of this, we help unify some of the results that have been presented in the literature. Secondly, if we have positive results for (2), then we have corresponding results for (1). One key conclusion of our results is that further developments on axiomatic and algorithmic aspects of hospital-doctor matching with regional quotas will result in corresponding results for school choice with diversity constraints.

Machine learning is increasingly being used in various applications that make decisions for individuals. For such applications, we need to strike a balance between achieving good prediction accuracy and making fair decisions with respect to a sensitive feature (e.g., race or gender), which is difficult in complex real-world scenarios. Existing methods measure the unfairness in such scenarios as {\it unfair causal effects} and constrain its mean to zero. Unfortunately, with these methods, the decisions are not necessarily fair for all individuals because even when the mean unfair effect is zero, unfair effects might be positive for some individuals and negative for others, which is discriminatory for them. To learn a classifier that is fair for all individuals, we define unfairness as the {\it probability of individual unfairness} (PIU) and propose to solve an optimization problem that constrains an upper bound on PIU. We theoretically illustrate why our method achieves individual fairness. Experimental results demonstrate that our method learns an individually fair classifier at a slight cost of prediction accuracy.

We explore the benefits of augmenting state-of-the-art model-free deep reinforcement algorithms with simple object representations. Following the Frostbite challenge posited by Lake et al. (2017), we identify object representations as a critical cognitive capacity lacking from current reinforcement learning agents. We discover that providing the Rainbow model (Hessel et al.,2018) with simple, feature-engineered object representations substantially boosts its performance on the Frostbite game from Atari 2600. We then analyze the relative contributions of the representations of different types of objects, identify environment states where these representations are most impactful, and examine how these representations aid in generalizing to novel situations.

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of behavior, such as ones which are deemed unsafe and are to be avoided, are best captured through constraints. We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent's overall reward while ensuring the agent satisfies a set of cost constraints. Using data generated from the current policy, FOCOPS first finds the optimal update policy by solving a constrained optimization problem in the nonparameterized policy space. FOCOPS then projects the update policy back into the parametric policy space. Our approach provides a guarantee for constraint satisfaction throughout training and is first-order in nature therefore extremely simple to implement. We provide empirical evidence that our algorithm achieves better performance on a set of constrained robotics locomotive tasks compared to current state of the art approaches.

One often reads that the complexities of anatomical pathology are now, or are soon to be unraveled by the latest machine learning technologies. Such incredible claims are bolstered by the experience of seeing a system classify histology images (or better, training one's own). It truly is remarkable that this is even possible. Yet, as this becomes a more common experience for the pathology community, it is likely that our current expectations and ambitions will be tempered by the constraints of reality. I remember being awe-struck at how realistic computer graphics were in the late 80's and early 90's.

In today's newsletter to all (subscribers and non-subscribers), we will share a best of the trend article (today we are sharing Google's ML trend prediction for 2020), machine learning pre-requisites and also a few plugs why you should subscribe. Only subscribers get easter eggs! These are important resources sent directly into their inbox. For example Winter Quarter, subscribers received url links self driving car resources and Pytorch textbook giveaways. January 2020 easter eggs are what is it like to be a machine learnist at work. Subscribers, your easter eggs will arrive soon!

The Thirty-Fourth annual meeting of AAAI just concluded in New York. As expected, it was a huge conference with thousands of AI Researches and practitioners in attendance. One big highlight was presentations from 2018 ACM Turing Award winners Geoffrey Hinton, Yann LeCun, and Yoshua Bengio as well as a panel discussion with Daniel Kahneman.

The name of this algorithm could be a little confusing in the sense that the Logistic Regression machine learning algorithm is for classification tasks and not regression problems. The name'Regression' here implies that a linear model is fit into the feature space. This algorithm applies a logistic function to a linear combination of features to predict the outcome of a categorical dependent variable based on predictor variables. Logistic regression algorithms help estimate the probability of falling into a specific level of the categorical dependent variable based on the given predictor variables. Suppose that you want to predict if there will be rain tomorrow in Toronto.

Oracle supercharged its efforts to take on cloud giants Amazon Web Services (AWS), Microsoft Azure, and Google Cloud Platform (GCP) and today launched a data science platform that runs as a native service on Oracle Cloud Infrastructure. The announcement marks the company's second cloud push of the new year. Last week Oracle announced its Generation 2 Cloud was available in five new regions including Jeddah, Saudi Arabia; Melbourne, Australia; Osaka, Japan; Montreal; and Amsterdam. The new Oracle's Cloud Infrastructure Data Science Platform uses elements of DataScience.com, The vendor claims the new offering can bring data scientists together and aid analysis with capabilities like shared projects, model catalogs, team security policies, reproducibility, and auditability.

Acoustically engineered to produce exceptional frequency response for an enhanced listening experience. Sweat proof, portable and lightweight headset can stay in your ears comfortably. Allowing you to control the volume, answer or end calls, control the playback of music and video with click of button and without taking your phone out.