4 papers
Influence Dynamics and Stagewise Data Attribution
Jin Hwa Lee, Matthew Smith, Maxwell Adam +1
Current training data attribution (TDA) methods treat the influence one sample has on another as static, but neural networks learn in distinct stages that exhibit changing patterns…
Bayesian Influence Functions for Hessian-Free Data Attribution
Philipp Alexander Kreer, Wilson Wu, Maxwell Adam +2
Classical influence functions face significant challenges when applied to deep neural networks, primarily due to non-invertible Hessians and high-dimensional parameter spaces. We p…
The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
Maxwell Adam, Zach Furman, Jesse Hoogland
We introduce the loss kernel, an interpretability method for measuring similarity between data points according to a trained neural network. The kernel is the covariance matrix of…
From Global to Local: A Scalable Benchmark for Local Posterior Sampling
Rohan Hitchcock, Jesse Hoogland
Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC) algorithms interact with this degene…