Zeke Xie, Zheng He, Quanzhi Zhu, Zengchang Qin
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent with respect to model overparameterization, they failed to recognize that sparsity may also cause double descent. In this paper, we have three main contributions. First, we report the novel sparse double descent phenomenon through extensive experiments. Second, for this phenomenon, we propose a novel learning distance interpretation that the curve of 2 learning distance of sparse models (from initialized parameters to final parameters) may correlate with the sparse double descent curve well and reflect generalization better than minima flatness. Third, in the context of sparse double descent, a winning ticket in the lottery ticket hypothesis surprisingly may not always win.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.08684")
get_code_for_paper("2206.08684")
have("2206.08684")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2206.08684.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2206.08684)
Connect an agent — have() is free.