How to train models that do not propagate discrimination?
Powerful machine learning models can automatize decisions in critical areas of human lives, such as criminal pre-trial detention and hiring. These models are often trained on large datasets of historical decisions. However, past discriminatory human behavior may have tainted these decisions and datasets with discimination. Therefore, it is imperative to ask how can we ensure … Continue reading "How to train models that do not propagate discrimination?"
Read MoreRegulating Face Recognition Technology: An Introduction
Face recognition technology, the ability for computers to identify people from photos or videos of their faces, has become increasingly controversial in the last few years. The software is rapidly becoming more common in applications from police work and surveillance to smart phone access, entertainment applications, and even medical diagnosis. There are those who wish … Continue reading "Regulating Face Recognition Technology: An Introduction"
Read MorePaper: Fairness Guarantees under Demographic Shift
Full Abstract: Recent studies found that using machine learning for social applications can lead to injustice in the form of racist, sexist, and otherwise unfair and discriminatory outcomes. To address this challenge, recent machine learning algorithms have been designed to limit the likelihood such unfair behavior occurs. However, these approaches typically assume the data used … Continue reading "Paper: Fairness Guarantees under Demographic Shift"
Read MorePaper: Parametric Bootstrap for Differentially Private Confidence Intervals
Full Abstract: The goal of this paper is to develop a practical and general-purpose approach to construct confidence intervals for differentially private parametric estimation. We find that the parametric bootstrap is a simple and effective solution. It cleanly reasons about variability of both the data sample and the randomized privacy mechanism and applies “out of … Continue reading "Paper: Parametric Bootstrap for Differentially Private Confidence Intervals"
Read MorePaper: Variational Marginal Particle Filters
Full Abstract: Variational inference for state space models (SSMs) is known to be hard in general. Recent works focus on deriving variational objectives for SSMs from unbiased sequential Monte Carlo estimators. We reveal that the marginal particle filter is obtained from sequential Monte Carlo by applying Rao-Blackwellization operations, which sacrifices the trajectory information for reduced … Continue reading "Paper: Variational Marginal Particle Filters"
Read MorePaper: Coresets for Classification – Simplified and Strengthened
We show how to sample a small subset of points from a larger dataset, such that if we solve logistic regression, hinge loss regression (i.e., soft margin SVM), or a number of other problems used to train linear classifiers on the sampled dataset, then we obtain a near optimal solution for the full dataset. This … Continue reading "Paper: Coresets for Classification – Simplified and Strengthened"
Read MorePaper: MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents
Most deep learning algorithms rely on error backpropagation, which is generally regarded as biologically implausible. An alternative way of training an artificial neural network is through treating each unit in the network as a reinforcement learning agent. As such, all units can be trained by REINFORCE. However, this learning method suffers from high variance and … Continue reading "Paper: MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents"
Read MorePaper: Turing Completeness of Bounded-Precision Recurrent Neural Networks
Previous works have proved that recurrent neural networks (RNNs) are Turing-complete. In the proofs, the RNNs allow for neurons with unbounded precision, which is neither practical in implementation nor biologically plausible. To remove this assumption, we propose a dynamically growing memory module made of neurons of fixed precision. We prove that a 54-neuron bounded-precision RNN … Continue reading "Paper: Turing Completeness of Bounded-Precision Recurrent Neural Networks"
Read MorePaper: Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback
This paper studies a cooperative multi-armed bandit problem with M agents cooperating together to solve the same instance of a K-armed stochastic bandit problem. The agents are heterogeneous in their limited access to a local subset of arms; and their decision-making rounds. The goal is to find the global optimal arm and agents are able … Continue reading "Paper: Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback"
Read MorePaper: Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems
In this work, we leverage machine-learned predictions to design competitive algorithms for online conversion problems with the goal of improving the competitive ratio when predictions are accurate (i.e., consistency), while also guaranteeing a worst-case competitive ratio regardless of the prediction quality (i.e., robustness). We unify the algorithmic design of both integral and fractional conversion problems, … Continue reading "Paper: Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems"
Read More