Skip to yearly menu bar Skip to main content


Estimating Training Data Influence by Tracing Gradient Descent

Garima Pruthi · Frederick Liu · Satyen Kale · Mukund Sundararajan

Poster Session 6 #1881

Keywords: [ Bandit Algorithms ] [ Algorithms ] [ Convex Optimization; The ] [ Algorithms; Algorithms -> Online Learning; Optimization -> Combinatorial Optimization; Optimization ]


We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the training process whenever the training example of interest was utilized. We provide a scalable implementation of TracIn via: (a) a first-order gradient approximation to the exact computation, (b) saved checkpoints of standard training procedures, and (c) cherry-picking layers of a deep neural network. In contrast with previously proposed methods, TracIn is simple to implement; all it needs is the ability to work with gradients, checkpoints, and loss functions. The method is general. It applies to any machine learning model trained using stochastic gradient descent or a variant of it, agnostic of architecture, domain and task. We expect the method to be widely useful within processes that study and improve training data.

Chat is not available.