Scaling Up Influence Functions
We address efficient calculation of influence functions for tracking predictions back to the training data. We propose and analyze a new approach to speeding up the inverse Hessian calculation based on Arnoldi iteration. With this improvement, we achieve, to the best of our knowledge, the first successful implementation of influence functions that scales to full-size (language and vision) Transformer models with several hundreds of millions of parameters. We evaluate our approach on image classification and sequence-to-sequence tasks with tens to a hundred of millions of training examples. Our code will be available at https://github.com/google-research/jax-influence.
Code (2)
Tasks
image-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting inverse Hessian vector products for calculating influence functions
Influence functions are a popular tool for attributing a model's output to training data. The traditional approach relies on the calculation of inverse Hessian-vector products (iHVP), but the classical solver "Linear tim…
The Central Role of the Loss Function in Reinforcement Learning
This paper illustrates the central role of loss functions in data-driven decision making, providing a comprehensive survey on their influence in cost-sensitive classification (CSC) and reinforcement learning (RL). We dem…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation
In robot imitation learning, influence functions provide a principled approach to quantify each demonstration's effect on robot task outcomes, yet scaling them to billion-parameter Vision-Language-Action (VLA) models is …
On the Interaction of Adaptive Population Control with Cumulative Step-Size Adaptation
Three state-of-the-art adaptive population control strategies (PCS) are theoretically and empirically investigated for a multi-recombinative, cumulative step-size adaptation Evolution Strategy $(\mu/\mu_I, \lambda)$-CSA-…
The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions
We introduce the Banach-Butterfly Invariant (BBT), an influence-adaptive Banach geometry on the Walsh-Hadamard butterfly factorization. For a Boolean function $f:\{-1,+1\}^n\to\{-1,+1\}$ with coordinate influences $\math…