Zobrazeno 1 - 10
of 1 181
pro vyhledávání: '"Park, Sung Min"'
Autor:
Georgiev, Kristian, Rinberg, Roy, Park, Sung Min, Garg, Shivam, Ilyas, Andrew, Madry, Aleksander, Neel, Seth
Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work shows that exi
Externí odkaz:
http://arxiv.org/abs/2410.23232
A recent surge of research in many-body quantum entanglement has uncovered intriguing properties of quantum many-body systems. A prime example is the modular commutator, which can extract a topological invariant from a single wave function. Here, we
Externí odkaz:
http://arxiv.org/abs/2407.11130
Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data-that is, identifying specific training examples which caused an image to
Externí odkaz:
http://arxiv.org/abs/2312.06205
Autor:
Leclerc, Guillaume, Ilyas, Andrew, Engstrom, Logan, Park, Sung Min, Salman, Hadi, Madry, Aleksander
We present FFCV, a library for easy and fast machine learning model training. FFCV speeds up model training by eliminating (often subtle) data bottlenecks from the training process. In particular, we combine techniques such as an efficient file stora
Externí odkaz:
http://arxiv.org/abs/2306.12517
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy. Th
Externí odkaz:
http://arxiv.org/abs/2303.14186
With recent achievements in tasks requiring context awareness, foundation models have been adopted to treat large-scale data from electronic health record (EHR) systems. However, previous clinical recommender systems based on foundation models have a
Externí odkaz:
http://arxiv.org/abs/2302.00612
We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizing this goal as one of finding distinguishing feature transformations,
Externí odkaz:
http://arxiv.org/abs/2211.12491
It is commonly believed that in transfer learning including more pre-training data translates into better performance. However, recent evidence suggests that removing data from the source dataset can actually help too. In this work, we take a closer
Externí odkaz:
http://arxiv.org/abs/2207.05739
Publikováno v:
In Biosensors and Bioelectronics 15 September 2024 260
