5 papers
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety…
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
Ameya Prabhu, Vishaal Udandarao, Philip Torr +3
Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies. In ou…
Random Representations Outperform Online Continually Learned Representations
Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru +3
Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the e…
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh +5
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for…
Corrective Machine Unlearning
Shashwat Goel, Ameya Prabhu, Philip Torr +2
Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do i…