The paper establishes that the optimal excess risk for ε-unlearning is the usual statistical error plus an unlearning penalty that interpolates between retraining-from-scratch and an exponentially smaller term as ε/d grows, with matching bounds for mean estimation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Kiko is a protocol-based agent programming model with operational semantics proving that agents written in it are protocol compliant and can enact any protocol.
The Internet now operates primarily on DNS names for services while IP addresses function only as ephemeral routing locators, creating an unplanned mismatch with the original TCP/IP address-based architecture.
citing papers explorer
-
Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses
The paper establishes that the optimal excess risk for ε-unlearning is the usual statistical error plus an unlearning penalty that interpolates between retraining-from-scratch and an exponentially smaller term as ε/d grows, with matching bounds for mean estimation.
-
Kiko: Programming Agents to Enact Interaction Protocols
Kiko is a protocol-based agent programming model with operational semantics proving that agents written in it are protocol compliant and can enact any protocol.
-
The Internet Runs on Names
The Internet now operates primarily on DNS names for services while IP addresses function only as ephemeral routing locators, creating an unplanned mismatch with the original TCP/IP address-based architecture.