Stochastic Gradient Descent
Stochastic Gradient Descent is an optimization algorithm that updates the parameters of a model iteratively based on the gradient of the loss function with respect to a randomly selected subset of data.
Category: Concepts
Bayesian Optimization
Bayesian Optimization is a strategy for the optimization of objective functions that are expensive to evaluate, using a probabilistic model to make decisions about where to sample next.
Conjugate Gradient
Conjugate Gradient is an iterative method for solving large systems of linear equations, particularly those that are symmetric and positive-definite.
Accuracy-Fairness Trade-off
The balance between maintaining high accuracy in predictions and ensuring fairness across different demographic groups.
Gaussian Process
A Gaussian Process is a collection of random variables, any finite number of which have a joint Gaussian distribution, used for regression and classification tasks.
Tractable Optimization Framework
A structured approach to optimization that allows for efficient computation and solution finding, particularly in complex problems.
Fairness in Classification
The principle of ensuring that classification models do not discriminate against individuals based on sensitive attributes.
Closed-form Optimal Mechanism
A mathematical formulation that provides an exact solution to a problem without the need for iterative approximation.
top-k rankings
Top-k rankings refer to the process of identifying the top k most important features or predictions based on their attribution scores.
Local Differential Privacy
A privacy-preserving technique that allows data to be collected and analyzed while ensuring that individual data points remain confidential.