Martin Gonzalez, Nelson Fernandez, Thuy Tran, Elies Gherbi, Hatem Hajri, Nader Masmoudi
We lifted 3 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 |
|---|---|---|
| nfsrules/seeds | canonical | 0 of 2 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| parse_int_list | Ran | this paper's copy was not recorded; identical code first harvested from newbeeer/stf pointer only · get_code("cacd4f6ec202d9b4") |
| ETD_ERK_SOLVER | Not yet run | nfsrules/seeds/seeds_lib/methods/etd_erk.py pointer only (licence: NONE) · get_code("2783993e9a8f04b4") |
| sampler | Not yet run | nfsrules/seeds/generate.py pointer only (licence: NONE) · get_code("2f8e508ca46e108e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A potent class of generative models known as Diffusion Probabilistic Models (DPMs) has become prominent. A forward diffusion process adds gradually noise to data, while a model learns to gradually denoise. Sampling from pre-trained DPMs is obtained by solving differential equations (DE) defined by the learnt model, a process which has shown to be prohibitively slow. Numerous efforts on speeding-up this process have consisted on crafting powerful ODE solvers. Despite being quick, such solvers do not usually reach the optimal quality achieved by available slow SDE solvers. Our goal is to propose SDE solvers that reach optimal quality without requiring several hundreds or thousands of NFEs to achieve that goal. We propose Stochastic Explicit Exponential Derivative-free Solvers (SEEDS), improving and generalizing Exponential Integrator approaches to the stochastic case on several frameworks. After carefully analyzing the formulation of exact solutions of diffusion SDEs, we craft SEEDS to analytically compute the linear part of such solutions. Inspired by the Exponential Time-Differencing method, SEEDS use a novel treatment of the stochastic components of solutions, enabling the analytical computation of their variance, and contains high-order terms allowing to reach optimal quality sampling ∼ 3-5× faster than previous SDE methods. We validate our approach on several image generation benchmarks, showing that SEEDS outperform or are competitive with previous SDE solvers. Contrary to the latter, SEEDS are derivative and training free, and we fully prove strong convergence guarantees for them. Our code is publicly available in this link.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.14267")
get_code_for_paper("2305.14267")
have("2305.14267")
Connect an agent — have() is free.