G De Luca, Eva Silverstein
We lifted 1 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| gbdl/bbi | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| BBI | Ran | gbdl/bbi/inflation.py code served (permissive licence) · get_code("6580b3d52f27dd93") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a specific algorithm with good performance on machine learning and PDE-solving tasks, including generalization. It cannot stop at a high local minimum, an advantage in non-convex loss functions, and proceeds faster than GD+momentum in shallow valleys.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2201.11137")
get_code_for_paper("2201.11137")
have("2201.11137")
Connect an agent — have() is free.