Guanya Shi, Yiheng Lin, Yisong Yue, Adam Wierman
We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| GuanyaShi/NeurIPS-2020-Online-Optimization-and-Competitive-Control | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| best_linear | Ran | GuanyaShi/NeurIPS-2020-Online-Optimization-and-Competitive-Control/utils_1d.py pointer only (licence: NONE) · get_code("def209e0a2934b07") |
| cost_linear | Ran | GuanyaShi/NeurIPS-2020-Online-Optimization-and-Competitive-Control/utils_1d.py pointer only (licence: NONE) · get_code("2cc8e4ed678028d5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hitting cost and a switching cost that depends on the previous p decisions. This setting generalizes Smoothed Online Convex Optimization. The proposed approach, Optimistic Regularized Online Balanced Descent, achieves a constant, dimension-free competitive ratio. Further, we show a connection between online optimization with memory and online control with adversarial disturbances. This connection, in turn, leads to a new constant-competitive policy for a rich class of online control problems. 2 [23,30]. The goal of the online learner is to minimize its total cost over T rounds: cost(ALG) = T t=1 f t (y t ) + c(y t , y t-1 ).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.05318")
get_code_for_paper("2002.05318")
have("2002.05318")
Connect an agent — have() is free.