Second-order optimizers retain residual geometric memory in their state after unlearning that first-order metrics miss, and only controlled eigendecay perturbations fully erase it.
Byrd, Peihuang Lu, Jorge Nocedal, and Ciyou Zhu
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A majorization-minimization framework turns IRT into scalable matrix factorization subproblems for LLM evaluation, delivering orders-of-magnitude speedups with identifiability guarantees.
LLM planning in four-in-a-row is myopic: move choices match a shallow model that ignores deep nodes expanded in reasoning traces.
Develops randomized-subspace Nesterov accelerated gradient methods with accelerated oracle-complexity guarantees for smooth convex optimization under matrix smoothness and sketch moment assumptions.
citing papers explorer
-
Shape of Memory: a Geometric Analysis of Machine Unlearning in Second-Order Optimizers
Second-order optimizers retain residual geometric memory in their state after unlearning that first-order metrics miss, and only controlled eigendecay perturbations fully erase it.
-
An Interpretable and Scalable Framework for Evaluating Large Language Models
A majorization-minimization framework turns IRT into scalable matrix factorization subproblems for LLM evaluation, delivering orders-of-magnitude speedups with identifiability guarantees.
-
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
LLM planning in four-in-a-row is myopic: move choices match a shallow model that ignores deep nodes expanded in reasoning traces.
-
Randomized Subspace Nesterov Accelerated Gradient
Develops randomized-subspace Nesterov accelerated gradient methods with accelerated oracle-complexity guarantees for smooth convex optimization under matrix smoothness and sketch moment assumptions.