Skip to main content

🏢 Meta

Robust Gaussian Processes via Relevance Pursuit
·2238 words·11 mins· loading · loading
Machine Learning Robustness 🏢 Meta
Robust Gaussian Processes via Relevance Pursuit tackles noisy data by cleverly inferring data-point specific noise levels, leading to more accurate predictions.
Public-data Assisted Private Stochastic Optimization: Power and Limitations
·337 words·2 mins· loading · loading
AI Generated AI Theory Privacy 🏢 Meta
Leveraging public data enhances differentially private (DP) learning, but its limits are unclear. This paper establishes tight theoretical bounds for DP stochastic convex optimization, revealing when …
On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
·2336 words·11 mins· loading · loading
AI Generated Machine Learning Active Learning 🏢 Meta
New active learning algorithm, Adaptive-Weight Sampling (AWS), achieves faster convergence with theoretical guarantees, improving data efficiency for machine learning.
Model Collapse Demystified: The Case of Regression
·1683 words·8 mins· loading · loading
AI Theory Generalization 🏢 Meta
Training AI models on AI-generated data leads to performance degradation, known as model collapse. This paper offers analytical formulas that precisely quantify this effect in high-dimensional regress…
Déjà Vu Memorization in Vision–Language Models
·2200 words·11 mins· loading · loading
Multimodal Learning Vision-Language Models 🏢 Meta
Vision-language models (VLMs) memorize training data, impacting generalization. This paper introduces ‘déjà vu memorization,’ a novel method measuring this, revealing significant memorization even in…