Tao Qin, Tie-Yan Liu, Chang Liu, Haoyue Tang, Jintao Wang
We lifted 9 functions out of this paper's own repositories and ran 7 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 |
|---|---|---|
| changliu00/cygen | canonical | 7 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| CyGen | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("e84b055f469eaec5") |
| SampleGradContainer | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("6e8e63560e1504bd") |
| compute_loss | Ran | changliu00/cygen/main_image.py code served (permissive licence) · get_code("3bca7eb82cff3d2d") |
| jacobian_normF2 | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("401936e904a628c2") |
| smart_grad | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("6b8b7358fd0a9717") |
| track_var | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("a2feae0e8bfc2fd1") |
| track_var | Ran | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("f76225cb9e3de0b7") |
| smart_grad | Not yet run | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("6a6067ace5950671") |
| solve_vec | Not yet run | changliu00/cygen/methods/cygen.py code served (permissive licence) · get_code("b291aa12c984e8d6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We study whether and how can we model a joint distribution p(x, z) using two conditional models p(x|z) and q(z|x) that form a cycle. This is motivated by the observation that deep generative models, in addition to a likelihood model p(x|z), often also use an inference model q(z|x) for extracting representation, but they rely on a usually uninformative prior distribution p(z) to define a joint distribution, which may render problems like posterior collapse and manifold mismatch. To explore the possibility to model a joint distribution using only p(x|z) and q(z|x), we study their compatibility and determinacy, corresponding to the existence and uniqueness of a joint distribution whose conditional distributions coincide with them. We develop a general theory for operable equivalence criteria for compatibility, and sufficient conditions for determinacy. Based on the theory, we propose a novel generative modeling framework CyGen that only uses the two cyclic conditional models. We develop methods to achieve compatibility and determinacy, and to use the conditional models to fit and generate data. With the prior constraint removed, CyGen better fits data and captures more representative features, supported by both synthetic and real-world experiments.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.15962")
get_code_for_paper("2106.15962")
have("2106.15962")
Connect an agent — have() is free.