English
Related papers

Related papers: Scaling Up Influence Functions

200 papers

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

Artificial Intelligence · Computer Science 2025-04-03 Theodoros Aivalis , Iraklis A. Klampanos , Antonis Troumpoukis , Joemon M. Jose

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

Sub-sampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the…

Machine Learning · Statistics 2017-09-07 Daniel Ting , Eric Brochu

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

In this paper, we study how to shape opinions in social networks when the matrix of interactions is unknown. We consider classical opinion dynamics with some stubborn agents and the possibility of continuously influencing the opinions of a…

Social and Information Networks · Computer Science 2019-10-22 Vivek Borkar , Alexandre Reiffers-Masson

This paper develops a data-driven inverse reinforcement learning technique for a class of linear systems to estimate the cost function of an agent online, using input-output measurements. A simultaneous state and parameter estimator is…

Systems and Control · Computer Science 2021-07-07 Rushikesh Kamalapurkar

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance. We find that more pre-training…

Computer Vision and Pattern Recognition · Computer Science 2018-12-13 Jiquan Ngiam , Daiyi Peng , Vijay Vasudevan , Simon Kornblith , Quoc V. Le , Ruoming Pang

Gaussian processes with derivative information are useful in many settings where derivative information is available, including numerous Bayesian optimization and regression tasks that arise in the natural sciences. Incorporating derivative…

Machine Learning · Computer Science 2021-07-12 Misha Padidar , Xinran Zhu , Leo Huang , Jacob R. Gardner , David Bindel

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common…

Machine Learning · Computer Science 2022-12-21 Yajie Bao , Yang Li , Shao-Lun Huang , Lin Zhang , Lizhong Zheng , Amir Zamir , Leonidas Guibas

In this paper we describe an efficient method for providing a regression model with a sense of curiosity about its data. In the field of machine learning, our framework for representing curiosity is called Active Learning, which concerns…

Machine Learning · Computer Science 2025-03-19 Frederik Eaton

Simulating trajectories of virtual crowds is a commonly encountered task in Computer Graphics. Several recent works have applied Reinforcement Learning methods to animate virtual agents, however they often make different design choices when…

Machine Learning · Computer Science 2022-09-21 Ariel Kwiatkowski , Vicky Kalogeiton , Julien Pettré , Marie-Paule Cani

Influence operations are large-scale efforts to manipulate public opinion. The rapid detection and disruption of these operations is critical for healthy public discourse. Emergent AI technologies may enable novel operations which evade…

Machine Learning · Computer Science 2023-05-29 Nicholas A. Gabriel , David A. Broniatowski , Neil F. Johnson

Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying training examples "responsible" for a prediction so that, for…

Machine Learning · Computer Science 2023-05-29 Andrea Schioppa , Katja Filippova , Ivan Titov , Polina Zablotskaia

This paper provides general matrix formulas for computing the score function, the (expected and observed) Fisher information and the $\Delta$ matrices (required for the assessment of local influence) for a quite general model which includes…

Methodology · Statistics 2021-09-17 Alexandre G. Patriota

Efforts to model viral cascades provide a vital view into how they form and spread. A range of methods, such as Multivariate Hawkes Processes or network inference algorithms, attempt to decompose cascades into constituent components via…

Social and Information Networks · Computer Science 2023-02-28 Nick Hagar , Laila Wahedi , Eric Dunford

Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of…

We study gradient flow on the multi-index regression problem for high-dimensional Gaussian data. Multi-index functions consist of a composition of an unknown low-rank linear projection and an arbitrary unknown, low-dimensional link…

Machine Learning · Statistics 2023-11-03 Alberto Bietti , Joan Bruna , Loucas Pillaud-Vivien

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Sheng-Yu Wang , Aaron Hertzmann , Alexei A Efros , Richard Zhang , Jun-Yan Zhu
‹ Prev 1 4 5 6 7 8 10 Next ›