no code implementations • 27 Mar 2024 • Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto
To reduce risks of leaking private information contained in the retrieved set, we introduce Copy-Protected generation with Retrieval (CPR), a new method for RAG with strong copyright protection guarantees in a mixed-private setting for diffusion models. CPR allows to condition the output of diffusion models on a set of retrieved images, while also guaranteeing that unique identifiable information about those example is not exposed in the generated outputs.
no code implementations • 2 Aug 2023 • Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference time.
no code implementations • 16 Jul 2023 • Tian Yu Liu, Aditya Golatkar, Stefano Soatto
We introduce Tangent Attention Fine-Tuning (TAFT), a method for fine-tuning linearized transformers obtained by computing a First-order Taylor Expansion around a pre-trained initialization.
no code implementations • ICCV 2023 • Yonatan Dukler, Benjamin Bowman, Alessandro Achille, Aditya Golatkar, Ashwin Swaminathan, Stefano Soatto
We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of training samples from the trained model.
no code implementations • 23 Nov 2022 • Tian Yu Liu, Aditya Golatkar, Stefano Soatto, Alessandro Achille
We propose a lightweight continual learning method which incorporates information from specialized datasets incrementally, by integrating it along the vector field of "generalist" models.
no code implementations • 1 Jul 2022 • Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas Diggavi, Stefano Soatto
We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI).
no code implementations • CVPR 2022 • Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off.
no code implementations • 25 Jun 2021 • Stephanie Tsuei, Aditya Golatkar, Stefano Soatto
We propose a method to estimate the uncertainty of the outcome of an image classifier on a given input datum.
no code implementations • CVPR 2021 • Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto
We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining information after forgetting.
no code implementations • CVPR 2021 • Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto
Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization.
1 code implementation • ECCV 2020 • Aditya Golatkar, Alessandro Achille, Stefano Soatto
We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions and can be extended to ensure forgetting in the activations of the network.
2 code implementations • CVPR 2020 • Aditya Golatkar, Alessandro Achille, Stefano Soatto
We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network.
no code implementations • NeurIPS 2019 • Aditya Golatkar, Alessandro Achille, Stefano Soatto
Deep neural networks (DNNs), however, challenge this view: We show that removing regularization after an initial transient period has little effect on generalization, even if the final loss landscape is the same as if there had been no regularization.
1 code implementation • 7 Sep 2018 • Rudrajit Das, Aditya Golatkar, Suyash P. Awate
In this paper, we propose a new method to perform Sparse Kernel Principal Component Analysis (SKPCA) and also mathematically analyze the validity of SKPCA.
1 code implementation • 22 Feb 2018 • Aditya Golatkar, Deepak Anand, Amit Sethi
In this paper, we propose a deep learning-based method for classification of H&E stained breast tissue images released for BACH challenge 2018 by fine-tuning Inception-v3 convolutional neural network (CNN) proposed by Szegedy et al.