Roger Baker Grosse

Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization

Distributional Training Data Attribution: What do Influence Functions Sample?

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Better Training Data Attribution via Better Inverse Hessian-Vector Products

Large-Scale Training Data Attribution with Efficient Influence Functions

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference

Fast Fractional Natural Gradient Descent using Learnable Spectral Factorizations