2 citations · 3 across the 5 of their papers we have counts for
3 papers · 1 filter
Gradient Equilibrium in Online Learning: Theory and Applications
Anastasios N. Angelopoulos, Michael I. Jordan, Ryan J. Tibshirani
We present a new perspective on online learning that we refer to as gradient equilibrium: a sequence of iterates achieves gradient equilibrium if the average of gradients of losses…
Automatically Adaptive Conformal Risk Control
Vincent Blot, Anastasios N Angelopoulos, Michael I Jordan +1
Science and technology have a growing need for effective mechanisms that ensure reliable, controlled performance from black-box machine learning algorithms. These performance guara…
AutoEval Done Right: Using Synthetic Data for Model Evaluation
Pierre Boyeau, Anastasios N. Angelopoulos, Nir Yosef +2
The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of h…