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.
We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis as well as tools from stochastic calculus, in order to derive convergence bounds for various types of non-convex functions. Guided by such analysis, we show that the same Lyapunov arguments hold in discrete-time, leading to matching rates. In addition, we use these models and Ito calculus to infer novel insights on the dynamics of SGD, proving that a decreasing learning rate acts as time warping or, equivalently, as landscape stretching.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1810.02565")
get_code_for_paper("1810.02565")
have("1810.02565")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1810.02565.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1810.02565)
Connect an agent — have() is free.