We lifted 23 functions out of this paper's own repositories and ran 22 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 |
|---|---|---|
| diffprog/code | canonical | 22 of 23 |
| Function | Status | Where it lives |
|---|---|---|
| and_op | Ran | diffprog/code/control_flows/plot_logical_ops_3d.py code served (permissive licence) · get_code("587d28cddf001d22") |
| argmax | Ran | diffprog/code/control_flows/plot_soft_thresholding.py code served (permissive licence) · get_code("802c2203920ee74b") |
| chain_log_sum | Ran | diffprog/code/graphical_models/inference_chain.py code served (permissive licence) · get_code("f2d5d8a5fd1be3c9") |
| chain_marginal | Ran | diffprog/code/graphical_models/inference_chain.py code served (permissive licence) · get_code("7aa9a0e7f0c35c60") |
| chain_product | Ran | diffprog/code/graphical_models/inference_chain.py code served (permissive licence) · get_code("46817697c062b78f") |
| colorline | Ran | diffprog/code/differentiating_integration/plot_ode_regression.py code served (permissive licence) · get_code("ac4084b445f0372b") |
| fun | Ran | diffprog/code/control_flows/plot_global_vs_local_smoothing.py code served (permissive licence) · get_code("13c7a0f0304259eb") |
| gaussian_cdf | Ran | diffprog/code/control_flows/plot_soft_comparison.py code served (permissive licence) · get_code("7a10f8d6f8e878d2") |
| gaussian_pdf | Ran | diffprog/code/control_flows/plot_stochastic_process_perspective.py code served (permissive licence) · get_code("b14f8c6c86585a4e") |
| get_compa_ops | Ran | diffprog/code/control_flows/plot_compa_ops.py code served (permissive licence) · get_code("d2f49ba064bce628") |
| get_mean_colormap | Ran | diffprog/code/differentiating_integration/plot_ode_regression.py code served (permissive licence) · get_code("fbed1f8b664b20d4") |
| get_relaxation_logical_op | Ran | diffprog/code/control_flows/plot_logical_ops.py code served (permissive licence) · get_code("b8aba2e639831d0e") |
| heaviside | Ran | diffprog/code/control_flows/plot_soft_comparison.py code served (permissive licence) · get_code("bbda47f128c79ae1") |
| ifelse | Ran | diffprog/code/control_flows/bubble_sort.py code served (permissive licence) · get_code("a9bb014b256b8027") |
| kernel | Ran | diffprog/code/data_struct/plot_dict_kernel_estim.py code served (permissive licence) · get_code("81dda7d4de68eb97") |
| kernel_smoother | Ran | diffprog/code/data_struct/plot_dict_kernel_estim.py code served (permissive licence) · get_code("2399ee8f6e7c8a6d") |
| local_smooth_fun | Ran | diffprog/code/control_flows/plot_global_vs_local_smoothing.py code served (permissive licence) · get_code("efeea7d6cead0548") |
| logistic | Ran | diffprog/code/control_flows/plot_soft_comparison.py code served (permissive licence) · get_code("8e99ad829bc70d6d") |
| or_op | Ran | diffprog/code/control_flows/plot_logical_ops_3d.py code served (permissive licence) · get_code("0cf69f025a2232ed") |
| sigmoid | Ran | diffprog/code/control_flows/plot_global_vs_local_smoothing.py code served (permissive licence) · get_code("1af82a1fc3f8bb07") |
| st | Ran | diffprog/code/control_flows/plot_soft_thresholding.py code served (permissive licence) · get_code("91f293d92f3b9828") |
| step | Ran | diffprog/code/control_flows/plot_soft_thresholding.py code served (permissive licence) · get_code("8bb9ef7b2dd1407c") |
| truncate_colormap | Not yet run | diffprog/code/differentiating_integration/plot_ode_regression.py code served (permissive licence) · get_code("252ab259ff2634ab") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of differentiable programming. This new programming paradigm enables end-to-end differentiation of complex computer programs (including those with control flows and data structures), making gradient-based optimization of program parameters possible. As an emerging paradigm, differentiable programming builds upon several areas of computer science and applied mathematics, including automatic differentiation, graphical models, optimization and statistics. This book presents a comprehensive review of the fundamental concepts useful for differentiable programming. We adopt two main perspectives, that of optimization and that of probability, with clear analogies between the two. Differentiable programming is not merely the differentiation of programs, but also the thoughtful design of programs intended for differentiation. By making programs differentiable, we inherently introduce probability distributions over their execution, providing a means to quantify the uncertainty associated with program outputs.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.14606")
get_code_for_paper("2403.14606")
have("2403.14606")
Connect an agent — have() is free.