6 citations · 10 across the 4 of their papers we have counts for
5 papers
Instance-Adaptive Online Multiclass Multicalibration
Zhiming Huang, Jamie Morgenstern, Aaron Roth +1
We study online multiclass multicalibration over rounds, and give an algorithm with beyond-worst-case guarantees. With possible outcomes, forecasts lie in a simplex of dime…
Defense via Consensus: Mitigating Subliminal Learning through Multi-Teacher Distillation
Adhyyan Narang, Artin Tajdini, Claire Zhang +1
Fine-tuning can introduce unwanted behaviors through deliberate poisoning or unexpected generalization from seemingly benign data. Because these effects may be difficult to anticip…
Instance-Adaptive Online Multicalibration
Zhiming Huang, Jamie Morgenstern, Aaron Roth +1
We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by adaptively r…
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
Martin Bertran, Shuai Tang, Michael Kearns +3
Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as…
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
Sampath Kannan, Jamie Morgenstern, Aaron Roth +2
Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of…