A Noise Optimum in Rehearsal-Free Continual Learning: Isolation, Mechanism, and Scope
Read the original on arXiv Machine Learning →The paper demonstrates that adding stochastic noise to a consolidation rule can improve a neural network’s retention of earlier tasks up to an optimal level, after which performance degrades, forming an inverted‑U relationship. Through simulations on related‑task continual‑learning benchmarks, the authors isolate the conditions that produce this optimum, showing it requires coherent restoration toward consolidated weights and is linked to the noise variance. The study further maps the scope of the effect, noting it depends on shared task structure and diminishes with more tasks, while a single‑seed hardware demonstration is referenced elsewhere.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.